32 commits

Author	SHA1	Message	Date
Danny Avila	935288f841	🏗️ feat: 3-Tier MCP Server Architecture with Config-Source Lazy Init (#12435) ... * feat: add MCPServerSource type, tenantMcpPolicy schema, and source-based dbSourced wiring - Add `tenantMcpPolicy` to `mcpSettings` in YAML config schema with `enabled`, `maxServersPerTenant`, `allowedTransports`, and `allowedDomains` - Add `MCPServerSource` type ('yaml' | 'config' | 'user') and `source` field to `ParsedServerConfig` - Change `dbSourced` determination from `!!config.dbId` to `config.source === 'user'` across MCPManager, ConnectionsRepository, UserConnectionManager, and MCPServerInspector - Set `source: 'user'` on all DB-sourced servers in ServerConfigsDB * feat: three-layer MCPServersRegistry with config cache and lazy init - Add `configCacheRepo` as third repository layer between YAML cache and DB for admin-defined config-source MCP servers - Implement `ensureConfigServers()` that identifies config-override servers from resolved `getAppConfig()` mcpConfig, lazily inspects them, and caches parsed configs with `source: 'config'` - Add `lazyInitConfigServer()` with timeout, stub-on-failure, and concurrent-init deduplication via `pendingConfigInits` map - Extend `getAllServerConfigs()` with optional `configServers` param for three-way merge: YAML → Config → User - Add `getServerConfig()` lookup through config cache layer - Add `invalidateConfigCache()` for clearing config-source inspection results on admin config mutations - Tag `source: 'yaml'` on CACHE-stored servers and `source: 'user'` on DB-stored servers in `addServer()` and `addServerStub()` * feat: wire tenant context into MCP controllers, services, and cache invalidation - Resolve config-source servers via `getAppConfig({ role, tenantId })` in `getMCPTools()` and `getMCPServersList()` controllers - Pass `ensureConfigServers()` results through `getAllServerConfigs()` for three-way merge of YAML + Config + User servers - Add tenant/role context to `getMCPSetupData()` and connection status routes via `getTenantId()` from ALS - Add `clearMcpConfigCache()` to `invalidateConfigCaches()` so admin config mutations trigger re-inspection of config-source MCP servers * feat: enforce tenantMcpPolicy on admin config mcpServers mutations - Add `validateMcpServerPolicy()` helper that checks mcpServers against operator-defined `tenantMcpPolicy` (enabled, maxServersPerTenant, allowedTransports, allowedDomains) - Wire validation into `upsertConfigOverrides` and `patchConfigField` handlers — rejects with 403 when policy is violated - Infer transport type from config shape (command → stdio, url protocol → websocket/sse, type field → streamable-http) - Validate server domains against policy allowlist when configured * revert: remove tenantMcpPolicy schema and enforcement The existing admin config CRUD routes already provide the mechanism for granular MCP server prepopulation (groups, roles, users). The tenantMcpPolicy gating adds unnecessary complexity that can be revisited if needed in the future. - Remove tenantMcpPolicy from mcpSettings Zod schema - Remove validateMcpServerPolicy helper and TenantMcpPolicy interface - Remove policy enforcement from upsertConfigOverrides and patchConfigField handlers * test: update test assertions for source field and config-server wiring - Use objectContaining in MCPServersRegistry reset test to account for new source: 'yaml' field on CACHE-stored configs - Add getTenantId and ensureConfigServers mocks to MCP route tests - Add getAppConfig mock to route test Config service mock - Update getMCPSetupData assertion to expect second options argument - Update getAllServerConfigs assertions for new configServers parameter * fix: disconnect active connections when config-source servers are evicted When admin config overrides change and config-source MCP servers are removed, the invalidation now proactively disconnects active connections for evicted servers instead of leaving them lingering until timeout. - Return evicted server names from invalidateConfigCache() - Disconnect app-level connections for evicted servers in clearMcpConfigCache() via MCPManager.appConnections.disconnect() * fix: address code review findings (CRITICAL, MAJOR, MINOR) CRITICAL fixes: - Scope configCacheRepo keys by config content hash to prevent cross-tenant cache poisoning when two tenants define the same server name with different configurations - Change dbSourced checks from `source === 'user'` to `source !== 'yaml' && source !== 'config'` so undefined source (pre-upgrade cached configs) fails closed to restricted mode MAJOR fixes: - Derive OAuth servers from already-computed mcpConfig instead of calling getOAuthServers() separately — config-source OAuth servers are now properly detected - Add parseInt radix (10) and NaN guard with fallback to 30_000 for CONFIG_SERVER_INIT_TIMEOUT_MS - Add CONFIG_CACHE_NAMESPACE to aggregate-key branch in ServerConfigsCacheFactory to avoid SCAN-based Redis stalls - Remove `if (role || tenantId)` guard in getMCPSetupData — config servers now always resolve regardless of tenant context MINOR fixes: - Extract resolveAllMcpConfigs() helper in mcp controller to eliminate 3x copy-pasted config resolution boilerplate - Distinguish "not initialized" from real errors in clearMcpConfigCache — log actual failures instead of swallowing - Remove narrative inline comments per style guide - Remove dead try/catch inside Promise.allSettled in ensureConfigServers (inner method never throws) - Memoize YAML server names to avoid repeated cacheConfigsRepo.getAll() calls per request Test updates: - Add ensureConfigServers mock to registry test fixtures - Update getMCPSetupData assertions for inline OAuth derivation * fix: address code review findings (CRITICAL, MAJOR, MINOR) CRITICAL fixes: - Break circular dependency: move CONFIG_CACHE_NAMESPACE from MCPServersRegistry to ServerConfigsCacheFactory - Fix dbSourced fail-closed: use source field when present, fall back to legacy dbId check when absent (backward-compatible with pre-upgrade cached configs that lack source field) MAJOR fixes: - Add CONFIG_CACHE_NAMESPACE to aggregate-key set in ServerConfigsCacheFactory to avoid SCAN-based Redis stalls - Add comprehensive test suite (ensureConfigServers.test.ts, 18 tests) covering lazy init, stub-on-failure, cross-tenant isolation via config hash keys, concurrent deduplication, merge order, and cache invalidation MINOR fixes: - Update MCPServerInspector test assertion for dbSourced change * fix: restore getServerConfig lookup for config-source servers (NEW-1) Add configNameToKey map that indexes server name → hash-based cache key for O(1) lookup by name in getServerConfig. This restores the config cache layer that was dropped when hash-based keys were introduced. Without this fix, config-source servers appeared in tool listings (via getAllServerConfigs) but getServerConfig returned undefined, breaking all connection and tool call paths. - Populate configNameToKey in ensureSingleConfigServer - Clear configNameToKey in invalidateConfigCache and reset - Clear stale read-through cache entries after lazy init - Remove dead code in invalidateConfigCache (config.title, key parsing) - Add getServerConfig tests for config-source server lookup * fix: eliminate configNameToKey race via caller-provided configServers param Replace the process-global configNameToKey map (last-writer-wins under concurrent multi-tenant load) with a configServers parameter on getServerConfig. Callers pass the pre-resolved config servers map directly — no shared mutable state, no cross-tenant race. - Add optional configServers param to getServerConfig; when provided, returns matching config directly without any global lookup - Remove configNameToKey map entirely (was the source of the race) - Extract server names from cache keys via lastIndexOf in invalidateConfigCache (safe for names containing colons) - Use mcpConfig[serverName] directly in getMCPTools instead of a redundant getServerConfig call - Add cross-tenant isolation test for getServerConfig * fix: populate read-through cache after config server lazy init After lazyInitConfigServer succeeds, write the parsed config to readThroughCache keyed by serverName so that getServerConfig calls from ConnectionsRepository, UserConnectionManager, and MCPManager.callTool find the config without needing configServers. Without this, config-source servers appeared in tool listings but every connection attempt and tool call returned undefined. * fix: user-scoped getServerConfig fallback to server-only cache key When getServerConfig is called with a userId (e.g., from callTool or UserConnectionManager), the cache key is serverName::userId. Config-source servers are cached under the server-only key (no userId). Add a fallback so user-scoped lookups find config-source servers in the read-through cache. * fix: configCacheRepo fallback, isUserSourced DRY, cross-process race CRITICAL: Add findInConfigCache fallback in getServerConfig so config-source servers remain reachable after readThroughCache TTL expires (5s). Without this, every tool call after 5s returned undefined for config-source servers. MAJOR: Extract isUserSourced() helper to mcp/utils.ts and replace all 5 inline dbSourced ternary expressions (MCPManager x2, ConnectionsRepository, UserConnectionManager, MCPServerInspector). MAJOR: Fix cross-process Redis race in lazyInitConfigServer — when configCacheRepo.add throws (key exists from another process), fall back to reading the existing entry instead of returning undefined. MINOR: Parallelize invalidateConfigCache awaits with Promise.all. Remove redundant .catch(() => {}) inside Promise.allSettled. Tighten dedup test assertion to toBe(1). Add TTL-expiry tests for getServerConfig (with and without userId). * feat: thread configServers through getAppToolFunctions and formatInstructionsForContext Add optional configServers parameter to getAppToolFunctions, getInstructions, and formatInstructionsForContext so config-source server tools and instructions are visible to agent initialization and context injection paths. Existing callers (boot-time init, tests) pass no argument and continue to work unchanged. Agent runtime paths can now thread resolved config servers from request context. * fix: stale failure stubs retry after 5 min, upsert for cross-process races - Add CONFIG_STUB_RETRY_MS (5 min) — stale failure stubs are retried instead of permanently disabling config-source servers after transient errors (DNS outage, cold-start race) - Extract upsertConfigCache() helper that tries add then falls back to update, preventing cross-process Redis races where a second instance's successful inspection result was discarded - Add test for stale-stub retry after CONFIG_STUB_RETRY_MS * fix: stamp updatedAt on failure stubs, null-guard callTool config, test cleanup - Add updatedAt: Date.now() to failure stubs in lazyInitConfigServer so CONFIG_STUB_RETRY_MS (5 min) window works correctly — without it, stubs were always considered stale (updatedAt ?? 0 → epoch → always expired) - Add null guard for rawConfig in MCPManager.callTool before passing to preProcessGraphTokens — prevents unsafe `as` cast on undefined - Log double-failure in upsertConfigCache instead of silently swallowing - Replace module-scope Date.now monkey-patch with jest.useFakeTimers / jest.setSystemTime / jest.useRealTimers in ensureConfigServers tests * fix: server-only readThrough fallback only returns truthy values Prevents a cached undefined from a prior no-userId lookup from short-circuiting the DB query on a subsequent userId-scoped lookup. * fix: remove findInConfigCache to eliminate cross-tenant config leakage The findInConfigCache prefix scan (serverName:*) could return any tenant's config after readThrough TTL expires, violating tenant isolation. Config-source servers are now ONLY resolvable through: 1. The configServers param (callers with tenant context from ALS) 2. The readThrough cache (populated by ensureSingleConfigServer, 5s TTL, repopulated on every HTTP request via resolveAllMcpConfigs) Connection/tool-call paths without tenant context rely exclusively on the readThrough cache. If it expires before the next HTTP request repopulates it, the server is not found — which is correct because there is no tenant context to determine which config to return. - Remove findInConfigCache method and its call in getServerConfig - Update server-only readThrough fallback to only return truthy values (prevents cached undefined from short-circuiting user-scoped DB lookup) - Update tests to document tenant isolation behavior after cache expiry * style: fix import order per AGENTS.md conventions Sort package imports shortest-to-longest, local imports longest-to-shortest across MCPServersRegistry, ConnectionsRepository, MCPManager, UserConnectionManager, and MCPServerInspector. * fix: eliminate cross-tenant readThrough contamination and TTL-expiry tool failures Thread pre-resolved serverConfig from tool creation context into callTool, removing dependency on the readThrough cache for config-source servers. This fixes two issues: - Cross-tenant contamination: the readThrough cache key was unscoped (just serverName), so concurrent multi-tenant requests for same-named servers would overwrite each other's entries - TTL expiry: tool calls happening >5s after config resolution would fail with "Configuration not found" because the readThrough entry had expired Changes: - Add optional serverConfig param to MCPManager.callTool — uses provided config directly, falling back to getServerConfig lookup for YAML/user servers - Thread serverConfig from createMCPTool through createToolInstance closure to callTool - Remove readThrough write from ensureSingleConfigServer — config-source servers are only accessible via configServers param (tenant-scoped) - Remove server-only readThrough fallback from getServerConfig - Increase config cache hash from 8 to 16 hex chars (64-bit) - Add isUserSourced boundary tests for all source/dbId combinations - Fix double Object.keys call in getMCPTools controller - Update test assertions for new getServerConfig behavior * fix: cache base configs for config-server users; narrow upsertConfigCache error handling - Refactor getAllServerConfigs to separate base config fetch (YAML + DB) from config-server layering. Base configs are cached via readThroughCacheAll regardless of whether configServers is provided, eliminating uncached MongoDB queries per request for config-server users - Narrow upsertConfigCache catch to duplicate-key errors only; infrastructure errors (Redis timeouts, network failures) now propagate instead of being silently swallowed, preventing inspection storms during outages * fix: restore correct merge order and document upsert error matching - Restore YAML → Config → User DB precedence in getAllServerConfigs (user DB servers have highest precedence, matching the JSDoc contract) - Add source comment on upsertConfigCache duplicate-key detection linking to the two cache implementations that define the error message * feat: complete config-source server support across all execution paths Wire configServers through the entire agent execution pipeline so config-source MCP servers are fully functional — not just visible in listings but executable in agent sessions. - Thread configServers into handleTools.js agent tool pipeline: resolve config servers from tenant context before MCP tool iteration, pass to getServerConfig, createMCPTools, and createMCPTool - Thread configServers into agent instructions pipeline: applyContextToAgent → getMCPInstructionsForServers → formatInstructionsForContext, resolved in client.js before agent context application - Add configServers param to createMCPTool and createMCPTools for reconnect path fallback - Add source field to redactServerSecrets allowlist for client UI differentiation of server tiers - Narrow invalidateConfigCache to only clear readThroughCacheAll (merged results), preserving YAML individual-server readThrough entries - Update context.spec.ts assertions for new configServers parameter * fix: add missing mocks for config-source server dependencies in client.test.js Mock getMCPServersRegistry, getAppConfig, and getTenantId that were added to client.js but not reflected in the test file's jest.mock declarations. * fix: update formatInstructionsForContext assertions for configServers param The test assertions expected formatInstructionsForContext to be called with only the server names array, but it now receives configServers as a second argument after the config-source server feature wiring. * fix: move configServers resolution before MCP tool loop to avoid TDZ configServers was declared with `let` after the first tool loop but referenced inside it via getServerConfig(), causing a ReferenceError temporal dead zone. Move declaration and resolution before the loop, using tools.some(mcpToolPattern) to gate the async resolution. * fix: address review findings — cache bypass, discoverServerTools gap, DRY - #2: getAllServerConfigs now always uses getBaseServerConfigs (cached via readThroughCacheAll) instead of bypassing it when configServers is present. Extracts user-DB entries from cached base by diffing against YAML keys to maintain YAML → Config → User DB merge order without extra MongoDB calls. - #3: Add configServers param to ToolDiscoveryOptions and thread it through discoverServerTools → getServerConfig so config-source servers are discoverable during OAuth reconnection flows. - #6: Replace inline import() type annotations in context.ts with proper import type { ParsedServerConfig } per AGENTS.md conventions. - #7: Extract resolveConfigServers(req) helper in MCP.js and use it from handleTools.js and client.js, eliminating the duplicated 6-line config resolution pattern. - #10: Restore removed "why" comment explaining getLoaded() vs getAll() choice in getMCPSetupData — documents non-obvious correctness constraint. - #11: Fix incomplete JSDoc param type on resolveAllMcpConfigs. * fix: consolidate imports, reorder constants, fix YAML-DB merge edge case - Merge duplicate @librechat/data-schemas requires in MCP.js into one - Move resolveConfigServers after module-level constants - Fix getAllServerConfigs edge case where user-DB entry overriding a YAML entry with the same name was excluded from userDbConfigs; now uses reference equality check to detect DB-overwritten YAML keys * fix: replace fragile string-match error detection with proper upsert method Add upsert() to IServerConfigsRepositoryInterface and all implementations (InMemory, Redis, RedisAggregateKey, DB). This eliminates the brittle error message string match ('already exists in cache') in upsertConfigCache that was the only thing preventing cross-process init races from silently discarding inspection results. Each implementation handles add-or-update atomically: - InMemory: direct Map.set() - Redis: direct cache.set() - RedisAggregateKey: read-modify-write under write lock - DB: delegates to update() (DB servers use explicit add() with ACL setup) * fix: wire configServers through remaining HTTP endpoints - getMCPServerById: use resolveAllMcpConfigs instead of bare getServerConfig - reinitialize route: resolve configServers before getServerConfig - auth-values route: resolve configServers before getServerConfig - getOAuthHeaders: accept configServers param, thread from callers - Update mcp.spec.js tests to mock getAllServerConfigs for GET by name * fix: thread serverConfig through getConnection for config-source servers Config-source servers exist only in configCacheRepo, not in YAML cache or DB. When callTool → getConnection → getUserConnection → getServerConfig runs without configServers, it returns undefined and throws. Fix by threading the pre-resolved serverConfig (providedConfig) from callTool through getConnection → getUserConnection → createUserConnectionInternal, using it as a fallback before the registry lookup. * fix: thread configServers through reinit, reconnect, and tool definition paths Wire configServers through every remaining call chain that creates or reconnects MCP server connections: - reinitMCPServer: accepts serverConfig and configServers, uses them for getServerConfig fallback, getConnection, and discoverServerTools - reconnectServer: accepts and passes configServers to reinitMCPServer - createMCPTools/createMCPTool: pass configServers to reconnectServer - ToolService.loadToolDefinitionsWrapper: resolves configServers from req, passes to both reinitMCPServer call sites - reinitialize route: passes serverConfig and configServers to reinitMCPServer * fix: address review findings — simplify merge, harden error paths, fix log labels - Simplify getAllServerConfigs merge: replace fragile reference-equality loop with direct spread { ...yamlConfigs, ...configServers, ...base } - Guard upsertConfigCache in lazyInitConfigServer catch block so cache failures don't mask the original inspection error - Deduplicate getYamlServerNames cold-start with promise dedup pattern - Remove dead `if (!mcpConfig)` guard in getMCPSetupData - Fix hardcoded "App server" in ServerConfigsCacheRedisAggregateKey error messages — now uses this.namespace for correct Config/App labeling - Remove misleading OAuth callback comment about readThrough cache - Move resolveConfigServers after module-level constants in MCP.js * fix: clear rejected yamlServerNames promise, fix config-source reinspect, fix reset log label - Clear yamlServerNamesPromise on rejection so transient cache errors don't permanently prevent ensureConfigServers from working - Skip reinspectServer for config-source servers (source: 'config') in reinitMCPServer — they lack a CACHE/DB storage location; retry is handled by CONFIG_STUB_RETRY_MS in ensureConfigServers - Use source field instead of dbId for storageLocation derivation - Fix remaining hardcoded "App" in reset() leaderCheck message * fix: persist oauthHeaders in flow state for config-source OAuth servers The OAuth callback route has no JWT auth context and cannot resolve config-source server configs. Previously, getOAuthHeaders would silently return {} for config-source servers, dropping custom token exchange headers. Now oauthHeaders are persisted in MCPOAuthFlowMetadata during flow initiation (which has auth context), and the callback reads them from the stored flow state with a fallback to the registry lookup for YAML/user-DB servers. * fix: update tests for getMCPSetupData null guard removal and ToolService mock - MCP.spec.js: update test to expect graceful handling of null mcpConfig instead of a throw (getAllServerConfigs always returns an object) - MCP.js: add defensive || {} for Object.entries(mcpConfig) in case of null from test mocks - ToolService.spec.js: add missing mock for ~/server/services/MCP (resolveConfigServers) * fix: address review findings — DRY, naming, logging, dead code, defensive guards - #1: Simplify getAllServerConfigs to single getBaseServerConfigs call, eliminating redundant double-fetch of cacheConfigsRepo.getAll() - #2: Add warning log when oauthHeaders absent from OAuth callback flow state - #3: Extract resolveAllMcpConfigs to MCP.js service layer; controller imports shared helper instead of reimplementing - #4: Rename _serverConfig/_provider to capturedServerConfig/capturedProvider in createToolInstance — these are actively used, not unused - #5: Log rejected results from ensureConfigServers Promise.allSettled so cache errors are visible instead of silently dropped - #6: Remove dead 'MCP config not found' error handlers from routes - #7: Document circular-dependency reason for dynamic require in clearMcpConfigCache - #8: Remove logger.error from withTimeout to prevent double-logging timeouts - #10: Add explicit userId guard in ServerConfigsDB.upsert with clear error message - #12: Use spread instead of mutation in addServer for immutability consistency - Add upsert mock to ensureConfigServers.test.ts DB mock - Update route tests for resolveAllMcpConfigs import change * fix: restore correct merge priority, use immutable spread, fix test mock - getAllServerConfigs: { ...configServers, ...base } so userDB wins over configServers, matching documented "User DB (highest)" priority - lazyInitConfigServer: use immutable spread instead of direct mutation for parsedConfig.source, consistent with addServer fix - Fix test to mock getAllServerConfigs as {} instead of null, remove unnecessary || {} defensive guard in getMCPSetupData * fix: error handling, stable hashing, flatten nesting, remove dead param - Wrap resolveConfigServers/resolveAllMcpConfigs in try/catch with graceful {} fallback so transient DB/cache errors don't crash tool pipeline - Sort keys in configCacheKey JSON.stringify for deterministic hashing regardless of object property insertion order - Flatten clearMcpConfigCache from 3 nested try-catch to early returns; document that user connections are cleaned up lazily (accepted tradeoff) - Remove dead configServers param from getAppToolFunctions (never passed) - Add security rationale comment for source field in redactServerSecrets * fix: use recursive key-sorting replacer in configCacheKey to prevent cross-tenant cache collision The array replacer in JSON.stringify acts as a property allowlist at every nesting depth, silently dropping nested keys like headers['X-API-Key'], oauth.client_secret, etc. Two configs with different nested values but identical top-level structure produced the same hash, causing cross-tenant cache hits and potential credential contamination. Switch to a function replacer that recursively sorts keys at all depths without dropping any properties. Also document the known gap in getOAuthServers: config-source OAuth servers are not covered by auto-reconnection or uninstall cleanup because callers lack request context. * fix: move clearMcpConfigCache to packages/api to eliminate circular dependency The function only depends on MCPServersRegistry and MCPManager, both of which live in packages/api. Import it directly from @librechat/api in the CJS layer instead of using dynamic require('~/config'). * chore: imports/fields ordering * fix: address review findings — error handling, targeted lookup, test gaps - Narrow resolveAllMcpConfigs catch to only wrap ensureConfigServers so getAppConfig/getAllServerConfigs failures propagate instead of masking infrastructure errors as empty server lists. - Use targeted getServerConfig in getMCPServerById instead of fetching all server configs for a single-server lookup. - Forward configServers to inner createMCPTool calls so reconnect path works for config-source servers. - Update getAllServerConfigs JSDoc to document disjoint-key design. - Add OAuth callback oauthHeaders fallback tests (flow state present vs registry fallback). - Add resolveConfigServers/resolveAllMcpConfigs unit tests covering happy path and error propagation. * fix: add getOAuthReconnectionManager mock to OAuth callback tests * chore: imports ordering	2026-03-28 10:36:43 -04:00
Danny Avila	8ba2bde5c1	📦 refactor: Consolidate DB models, encapsulating Mongoose usage in data-schemas (#11830) ... * chore: move database model methods to /packages/data-schemas * chore: add TypeScript ESLint rule to warn on unused variables * refactor: model imports to streamline access - Consolidated model imports across various files to improve code organization and reduce redundancy. - Updated imports for models such as Assistant, Message, Conversation, and others to a unified import path. - Adjusted middleware and service files to reflect the new import structure, ensuring functionality remains intact. - Enhanced test files to align with the new import paths, maintaining test coverage and integrity. * chore: migrate database models to packages/data-schemas and refactor all direct Mongoose Model usage outside of data-schemas * test: update agent model mocks in unit tests - Added `getAgent` mock to `client.test.js` to enhance test coverage for agent-related functionality. - Removed redundant `getAgent` and `getAgents` mocks from `openai.spec.js` and `responses.unit.spec.js` to streamline test setup and reduce duplication. - Ensured consistency in agent mock implementations across test files. * fix: update types in data-schemas * refactor: enhance type definitions in transaction and spending methods - Updated type definitions in `checkBalance.ts` to use specific request and response types. - Refined `spendTokens.ts` to utilize a new `SpendTxData` interface for better clarity and type safety. - Improved transaction handling in `transaction.ts` by introducing `TransactionResult` and `TxData` interfaces, ensuring consistent data structures across methods. - Adjusted unit tests in `transaction.spec.ts` to accommodate new type definitions and enhance robustness. * refactor: streamline model imports and enhance code organization - Consolidated model imports across various controllers and services to a unified import path, improving code clarity and reducing redundancy. - Updated multiple files to reflect the new import structure, ensuring all functionalities remain intact. - Enhanced overall code organization by removing duplicate import statements and optimizing the usage of model methods. * feat: implement loadAddedAgent and refactor agent loading logic - Introduced `loadAddedAgent` function to handle loading agents from added conversations, supporting multi-convo parallel execution. - Created a new `load.ts` file to encapsulate agent loading functionalities, including `loadEphemeralAgent` and `loadAgent`. - Updated the `index.ts` file to export the new `load` module instead of the deprecated `loadAgent`. - Enhanced type definitions and improved error handling in the agent loading process. - Adjusted unit tests to reflect changes in the agent loading structure and ensure comprehensive coverage. * refactor: enhance balance handling with new update interface - Introduced `IBalanceUpdate` interface to streamline balance update operations across the codebase. - Updated `upsertBalanceFields` method signatures in `balance.ts`, `transaction.ts`, and related tests to utilize the new interface for improved type safety. - Adjusted type imports in `balance.spec.ts` to include `IBalanceUpdate`, ensuring consistency in balance management functionalities. - Enhanced overall code clarity and maintainability by refining type definitions related to balance operations. * feat: add unit tests for loadAgent functionality and enhance agent loading logic - Introduced comprehensive unit tests for the `loadAgent` function, covering various scenarios including null and empty agent IDs, loading of ephemeral agents, and permission checks. - Enhanced the `initializeClient` function by moving `getConvoFiles` to the correct position in the database method exports, ensuring proper functionality. - Improved test coverage for agent loading, including handling of non-existent agents and user permissions. * chore: reorder memory method exports for consistency - Moved `deleteAllUserMemories` to the correct position in the exported memory methods, ensuring a consistent and logical order of method exports in `memory.ts`.	2026-03-21 14:28:53 -04:00
Danny Avila	fa9e1b228a	🪪 fix: MCP API Responses and OAuth Validation (#12217) ... * 🔒 fix: Validate MCP Configs in Server Responses * 🔒 fix: Enhance OAuth URL Validation in MCPOAuthHandler - Introduced validation for OAuth URLs to ensure they do not target private or internal addresses, enhancing security against SSRF attacks. - Updated the OAuth flow to validate both authorization and token URLs before use, ensuring compliance with security standards. - Refactored redirect URI handling to streamline the OAuth client registration process. - Added comprehensive error handling for invalid URLs, improving robustness in OAuth interactions. * 🔒 feat: Implement Permission Checks for MCP Server Management - Added permission checkers for MCP server usage and creation, enhancing access control. - Updated routes for reinitializing MCP servers and retrieving authentication values to include these permission checks, ensuring only authorized users can access these functionalities. - Refactored existing permission logic to improve clarity and maintainability. * 🔒 fix: Enhance MCP Server Response Validation and Redaction - Updated MCP route tests to use `toMatchObject` for better validation of server response structures, ensuring consistency in expected properties. - Refactored the `redactServerSecrets` function to streamline the removal of sensitive information, ensuring that user-sourced API keys are properly redacted while retaining their source. - Improved OAuth security tests to validate rejection of private URLs across multiple endpoints, enhancing protection against SSRF vulnerabilities. - Added comprehensive tests for the `redactServerSecrets` function to ensure proper handling of various server configurations, reinforcing security measures. * chore: eslint * 🔒 fix: Enhance OAuth Server URL Validation in MCPOAuthHandler - Added validation for discovered authorization server URLs to ensure they meet security standards. - Improved logging to provide clearer insights when an authorization server is found from resource metadata. - Refactored the handling of authorization server URLs to enhance robustness against potential security vulnerabilities. * 🔒 test: Bypass SSRF validation for MCP OAuth Flow tests - Mocked SSRF validation functions to allow tests to use real local HTTP servers, facilitating more accurate testing of the MCP OAuth flow. - Updated test setup to ensure compatibility with the new mocking strategy, enhancing the reliability of the tests. * 🔒 fix: Add Validation for OAuth Metadata Endpoints in MCPOAuthHandler - Implemented checks for the presence and validity of registration and token endpoints in the OAuth metadata, enhancing security by ensuring that these URLs are properly validated before use. - Improved error handling and logging to provide better insights during the OAuth metadata processing, reinforcing the robustness of the OAuth flow. * 🔒 refactor: Simplify MCP Auth Values Endpoint Logic - Removed redundant permission checks for accessing the MCP server resource in the auth-values endpoint, streamlining the request handling process. - Consolidated error handling and response structure for improved clarity and maintainability. - Enhanced logging for better insights during the authentication value checks, reinforcing the robustness of the endpoint. * 🔒 test: Refactor LeaderElection Integration Tests for Improved Cleanup - Moved Redis key cleanup to the beforeEach hook to ensure a clean state before each test. - Enhanced afterEach logic to handle instance resignations and Redis key deletion more robustly, improving test reliability and maintainability.	2026-03-13 23:18:56 -04:00
Danny Avila	fcb344da47	🛂 fix: MCP OAuth Race Conditions, CSRF Fallback, and Token Expiry Handling (#12171) ... * fix: Implement race conditions in MCP OAuth flow - Added connection mutex to coalesce concurrent `getUserConnection` calls, preventing multiple simultaneous attempts. - Enhanced flow state management to retry once when a flow state is missing, improving resilience against race conditions. - Introduced `ReauthenticationRequiredError` for better error handling when access tokens are expired or missing. - Updated tests to cover new race condition scenarios and ensure proper handling of OAuth flows. * fix: Stale PENDING flow detection and OAuth URL re-issuance PENDING flows in handleOAuthRequired now check createdAt age — flows older than 2 minutes are treated as stale and replaced instead of joined. Fixes the case where a leftover PENDING flow from a previous session blocks new OAuth initiation. authorizationUrl is now stored in MCPOAuthFlowMetadata so that when a second caller joins an active PENDING flow (e.g., the SSE-emitting path in ToolService), it can re-issue the URL to the user via oauthStart. * fix: CSRF fallback via active PENDING flow in OAuth callback When the OAuth callback arrives without CSRF or session cookies (common in the chat/SSE flow where cookies can't be set on streaming responses), fall back to validating that a PENDING flow exists for the flowId. This is safe because the flow was created server-side after JWT authentication and the authorization code is PKCE-protected. * test: Extract shared OAuth test server helpers Move MockKeyv, getFreePort, trackSockets, and createOAuthMCPServer into a shared helpers/oauthTestServer module. Enhance the test server with refresh token support, token rotation, metadata discovery, and dynamic client registration endpoints. Add InMemoryTokenStore for token storage tests. Refactor MCPOAuthRaceCondition.test.ts to import from shared helpers. * test: Add comprehensive MCP OAuth test modules MCPOAuthTokenStorage — 21 tests for storeTokens/getTokens with InMemoryTokenStore: encrypt/decrypt round-trips, expiry calculation, refresh callback wiring, ReauthenticationRequiredError paths. MCPOAuthFlow — 10 tests against real HTTP server: token refresh with stored client info, refresh token rotation, metadata discovery, dynamic client registration, full store/retrieve/expire/refresh lifecycle. MCPOAuthConnectionEvents — 5 tests for MCPConnection OAuth event cycle with real OAuth-gated MCP server: oauthRequired emission on 401, oauthHandled reconnection, oauthFailed rejection, token expiry detection. MCPOAuthTokenExpiry — 12 tests for the token expiry edge case: refresh success/failure paths, ReauthenticationRequiredError, PENDING flow CSRF fallback, authorizationUrl metadata storage, full re-auth cycle after refresh failure, concurrent expired token coalescing, stale PENDING flow detection. * test: Enhance MCP OAuth connection tests with cooldown reset Added a `beforeEach` hook to clear the cooldown for `MCPConnection` before each test, ensuring a clean state. Updated the race condition handling in the tests to properly clear the timeout, improving reliability in the event data retrieval process. * refactor: PENDING flow management and state recovery in MCP OAuth - Introduced a constant `PENDING_STALE_MS` to define the age threshold for PENDING flows, improving the handling of stale flows. - Updated the logic in `MCPConnectionFactory` and `FlowStateManager` to check the age of PENDING flows before joining or reusing them. - Modified the `completeFlow` method to return false when the flow state is deleted, ensuring graceful handling of race conditions. - Enhanced tests to validate the new behavior and ensure robustness against state recovery issues. * refactor: MCP OAuth flow management and testing - Updated the `completeFlow` method to log warnings when a tool flow state is not found during completion, improving error handling. - Introduced a new `normalizeExpiresAt` function to standardize expiration timestamp handling across the application. - Refactored token expiration checks in `MCPConnectionFactory` to utilize the new normalization function, ensuring consistent behavior. - Added a comprehensive test suite for OAuth callback CSRF fallback logic, validating the handling of PENDING flows and their staleness. - Enhanced existing tests to cover new expiration normalization logic and ensure robust flow state management. * test: Add CSRF fallback tests for active PENDING flows in MCP OAuth - Introduced new tests to validate CSRF fallback behavior when a fresh PENDING flow exists without cookies, ensuring successful OAuth callback handling. - Added scenarios to reject requests when no PENDING flow exists, when only a COMPLETED flow is present, and when a PENDING flow is stale, enhancing the robustness of flow state management. - Improved overall test coverage for OAuth callback logic, reinforcing the handling of CSRF validation failures. * chore: imports order * refactor: Update UserConnectionManager to conditionally manage pending connections - Modified the logic in `UserConnectionManager` to only set pending connections if `forceNew` is false, preventing unnecessary overwrites. - Adjusted the cleanup process to ensure pending connections are only deleted when not forced, enhancing connection management efficiency. * refactor: MCP OAuth flow state management - Introduced a new method `storeStateMapping` in `MCPOAuthHandler` to securely map the OAuth state parameter to the flow ID, improving callback resolution and security against forgery. - Updated the OAuth initiation and callback handling in `mcp.js` to utilize the new state mapping functionality, ensuring robust flow management. - Refactored `MCPConnectionFactory` to store state mappings during flow initialization, enhancing the integrity of the OAuth process. - Adjusted comments to clarify the purpose of state parameters in authorization URLs, reinforcing code readability. * refactor: MCPConnection with OAuth recovery handling - Added `oauthRecovery` flag to manage OAuth recovery state during connection attempts. - Introduced `decrementCycleCount` method to reduce the circuit breaker's cycle count upon successful reconnection after OAuth recovery. - Updated connection logic to reset the `oauthRecovery` flag after handling OAuth, improving state management and connection reliability. * chore: Add debug logging for OAuth recovery cycle count decrement - Introduced a debug log statement in the `MCPConnection` class to track the decrement of the cycle count after a successful reconnection during OAuth recovery. - This enhancement improves observability and aids in troubleshooting connection issues related to OAuth recovery. * test: Add OAuth recovery cycle management tests - Introduced new tests for the OAuth recovery cycle in `MCPConnection`, validating the decrement of cycle counts after successful reconnections. - Added scenarios to ensure that the cycle count is not decremented on OAuth failures, enhancing the robustness of connection management. - Improved test coverage for OAuth reconnect scenarios, ensuring reliable behavior under various conditions. * feat: Implement circuit breaker configuration in MCP - Added circuit breaker settings to `.env.example` for max cycles, cycle window, and cooldown duration. - Refactored `MCPConnection` to utilize the new configuration values from `mcpConfig`, enhancing circuit breaker management. - Improved code maintainability by centralizing circuit breaker parameters in the configuration file. * refactor: Update decrementCycleCount method for circuit breaker management - Changed the visibility of the `decrementCycleCount` method in `MCPConnection` from private to public static, allowing it to be called with a server name parameter. - Updated calls to `decrementCycleCount` in `MCPConnectionFactory` to use the new static method, improving clarity and consistency in circuit breaker management during connection failures and OAuth recovery. - Enhanced the handling of circuit breaker state by ensuring the method checks for the existence of the circuit breaker before decrementing the cycle count. * refactor: cycle count decrement on tool listing failure - Added a call to `MCPConnection.decrementCycleCount` in the `MCPConnectionFactory` to handle cases where unauthenticated tool listing fails, improving circuit breaker management. - This change ensures that the cycle count is decremented appropriately, maintaining the integrity of the connection recovery process. * refactor: Update circuit breaker configuration and logic - Enhanced circuit breaker settings in `.env.example` to include new parameters for failed rounds and backoff strategies. - Refactored `MCPConnection` to utilize the updated configuration values from `mcpConfig`, improving circuit breaker management. - Updated tests to reflect changes in circuit breaker logic, ensuring accurate validation of connection behavior under rapid reconnect scenarios. * feat: Implement state mapping deletion in MCP flow management - Added a new method `deleteStateMapping` in `MCPOAuthHandler` to remove orphaned state mappings when a flow is replaced, preventing old authorization URLs from resolving after a flow restart. - Updated `MCPConnectionFactory` to call `deleteStateMapping` during flow cleanup, ensuring proper management of OAuth states. - Enhanced test coverage for state mapping functionality to validate the new deletion logic.	2026-03-10 21:15:01 -04:00
Danny Avila	599f4a11f1	🛡️ fix: Secure MCP/Actions OAuth Flows, Resolve Race Condition & Tool Cache Cleanup (#11756) ... * 🔧 fix: Update OAuth error message for clarity - Changed the default error message in the OAuth error route from 'Unknown error' to 'Unknown OAuth error' to provide clearer context during authentication failures. * 🔒 feat: Enhance OAuth flow with CSRF protection and session management - Implemented CSRF protection for OAuth flows by introducing `generateOAuthCsrfToken`, `setOAuthCsrfCookie`, and `validateOAuthCsrf` functions. - Added session management for OAuth with `setOAuthSession` and `validateOAuthSession` middleware. - Updated routes to bind CSRF tokens for MCP and action OAuth flows, ensuring secure authentication. - Enhanced tests to validate CSRF handling and session management in OAuth processes. * 🔧 refactor: Invalidate cached tools after user plugin disconnection - Added a call to `invalidateCachedTools` in the `updateUserPluginsController` to ensure that cached tools are refreshed when a user disconnects from an MCP server after a plugin authentication update. This change improves the accuracy of tool data for users. * chore: imports order * fix: domain separator regex usage in ToolService - Moved the declaration of `domainSeparatorRegex` to avoid redundancy in the `loadActionToolsForExecution` function, improving code clarity and performance. * chore: OAuth flow error handling and CSRF token generation - Enhanced the OAuth callback route to validate the flow ID format, ensuring proper error handling for invalid states. - Updated the CSRF token generation function to require a JWT secret, throwing an error if not provided, which improves security and clarity in token generation. - Adjusted tests to reflect changes in flow ID handling and ensure robust validation across various scenarios.	2026-02-12 14:22:05 -05:00
Artyom Bogachenko	7844a93f8b	♻️ fix: use DOMAIN_CLIENT for MCP OAuth Redirects (#11057) ... Co-authored-by: Artyom Bogachenco <a.bogachenko@easyreport.ai>	2025-12-25 12:24:01 -05:00
Atef Bellaaj	99f8bd2ce6	🏗️ feat: Dynamic MCP Server Infrastructure with Access Control (#10787) ... * Feature: Dynamic MCP Server with Full UI Management * 🚦 feat: Add MCP Connection Status icons to MCPBuilder panel (#10805) * feature: Add MCP server connection status icons to MCPBuilder panel * refactor: Simplify MCPConfigDialog rendering in MCPBuilderPanel --------- Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com> Co-authored-by: Danny Avila <danny@librechat.ai> * fix: address code review feedback for MCP server management - Fix OAuth secret preservation to avoid mutating input parameter by creating a merged config copy in ServerConfigsDB.update() - Improve error handling in getResourcePermissionsMap to propagate critical errors instead of silently returning empty Map - Extract duplicated MCP server filter logic by exposing selectableServers from useMCPServerManager hook and using it in MCPSelect component * test: Update PermissionService tests to throw errors on invalid resource types - Changed the test for handling invalid resource types to ensure it throws an error instead of returning an empty permissions map. - Updated the expectation to check for the specific error message when an invalid resource type is provided. * feat: Implement retry logic for MCP server creation to handle race conditions - Enhanced the createMCPServer method to include retry logic with exponential backoff for handling duplicate key errors during concurrent server creation. - Updated tests to verify that all concurrent requests succeed and that unique server names are generated. - Added a helper function to identify MongoDB duplicate key errors, improving error handling during server creation. * refactor: StatusIcon to use CircleCheck for connected status - Replaced the PlugZap icon with CircleCheck in the ConnectedStatusIcon component to better represent the connected state. - Ensured consistent icon usage across the component for improved visual clarity. * test: Update AccessControlService tests to throw errors on invalid resource types - Modified the test for invalid resource types to ensure it throws an error with a specific message instead of returning an empty permissions map. - This change enhances error handling and improves test coverage for the AccessControlService. * fix: Update error message for missing server name in MCP server retrieval - Changed the error message returned when the server name is not provided from 'MCP ID is required' to 'Server name is required' for better clarity and accuracy in the API response. --------- Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com> Co-authored-by: Danny Avila <danny@librechat.ai>	2025-12-11 16:38:37 -05:00
Atef Bellaaj	ad6ba4b6d1	🧬 refactor: Wire Database Methods into MCP Package via Registry Pattern (#10715) ... * Refactor: MCPServersRegistry Singleton Pattern with Dependency Injection for DB methods consumption * refactor: error handling in MCP initialization and improve logging for MCPServersRegistry instance creation. - Added checks for mongoose instance in ServerConfigsDB constructor and refined error messages for clarity. - Reorder and use type imports --------- Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com> Co-authored-by: Danny Avila <danny@librechat.ai>	2025-12-11 16:37:12 -05:00
Atef Bellaaj	ef1b7f0157	🧩 refactor: Decouple MCP Config from Startup Config (#10689) ... * Decouple mcp config from start up config * Chore: Work on AI Review and Copilot Comments - setRawConfig is not needed since the private raw config is not needed any more - !!serversLoading bug fixed - added unit tests for route /api/mcp/servers - copilot comments addressed * chore: remove comments * chore: rename data-provider dir for MCP * chore: reorganize mcp specific query hooks * fix: consolidate imports for MCP server manager * chore: add dev-staging branch to frontend review workflow triggers * feat: add GitHub Actions workflow for building and pushing Docker images to GitHub Container Registry and Docker Hub * fix: update label for tag input in BookmarkForm tests to improve clarity --------- Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com> Co-authored-by: Danny Avila <danny@librechat.ai>	2025-12-11 16:36:34 -05:00
Danny Avila	24c76c6cb9	🛜 feat: Support Legacy OAuth Servers without .well-known Metadata (#10917) ... Adds support for MCP servers like StackOverflow that use OAuth but don't provide standard discovery metadata at .well-known endpoints. Changes: - Add fallback OAuth endpoints (/authorize, /token, /register) when discoverAuthorizationServerMetadata returns undefined - Add POST fallback in OAuth detection when HEAD returns non-401 (StackOverflow returns 405 for HEAD, 401 for POST) - Detect OAuth requirement from WWW-Authenticate: Bearer header even without resource_metadata URL - Add fallback /token endpoint for token refresh when metadata discovery fails - Add registration_endpoint to OAuthMetadata type This mirrors the MCP SDK's behavior where it gracefully falls back to default OAuth endpoint paths when .well-known metadata isn't available. Tests: - Add unit tests for detectOAuth.ts (POST fallback, Bearer detection) - Add unit tests for handler.ts (fallback metadata, fallback refresh) - Add StackOverflow to integration test servers Fixes OAuth flow for servers that: - Return 405 for HEAD requests (only support POST) - Return 401 with simple "Bearer" in WWW-Authenticate - Don't have .well-known/oauth-authorization-server endpoint - Use standard /authorize, /token, /register paths	2025-12-11 12:31:24 -05:00
Danny Avila	dd35f42073	🔒 feat: Idempotency Check for OAuth Flow Completion (#10468) ... * 🔒 feat: Implement idempotency check for OAuth flow completion - Added a check to prevent duplicate token exchanges if the OAuth flow has already been completed. - Updated the OAuth callback route to redirect appropriately when a completed flow is detected. - Refactored token storage logic to use original flow state credentials instead of updated ones. - Enhanced tests to cover the new idempotency behavior and ensure correct handling of OAuth flow states. * chore: add back scope for logging * refactor: Add isFlowStale method to FlowStateManager for stale flow detection - Implemented a new method to check if a flow is stale based on its age and status. - Updated MCPConnectionFactory to utilize the isFlowStale method for cleaning up stale OAuth flows. - Enhanced logging to provide more informative messages regarding flow status and age during cleanup. * test: Add unit tests for isFlowStale method in FlowStateManager - Implemented comprehensive tests for the isFlowStale method to verify its behavior across various flow statuses (PENDING, COMPLETED, FAILED) and age thresholds. - Ensured correct handling of edge cases, including flows with missing timestamps and custom stale thresholds. - Enhanced test coverage to validate the logic for determining flow staleness based on createdAt, completedAt, and failedAt timestamps.	2025-11-12 08:44:45 -05:00
Sean McGrath	b443254151	🔐 fix: persist new MCP oauth tokens properly (#10439) ... * fix: re-fetch OAuth flow state after completeOAuthFlow * test: add tests for MCP OAuth flow state bugs	2025-11-10 19:51:20 -05:00
Theo N. Truong	ce7e6edad8	🔄 refactor: MCP Registry System with Distributed Caching (#10191) ... * refactor: Restructure MCP registry system with caching - Split MCPServersRegistry into modular components: - MCPServerInspector: handles server inspection and health checks - MCPServersInitializer: manages server initialization logic - MCPServersRegistry: simplified registry coordination - Add distributed caching layer: - ServerConfigsCacheRedis: Redis-backed configuration cache - ServerConfigsCacheInMemory: in-memory fallback cache - RegistryStatusCache: distributed leader election state - Add promise utilities (withTimeout) replacing Promise.race patterns - Add comprehensive cache integration tests for all cache implementations - Remove unused MCPManager.getAllToolFunctions method * fix: Update OAuth flow to include user-specific headers * chore: Update Jest configuration to ignore additional test files - Added patterns to ignore files ending with .helper.ts and .helper.d.ts in testPathIgnorePatterns for cleaner test runs. * fix: oauth headers in callback * chore: Update Jest testPathIgnorePatterns to exclude helper files - Modified testPathIgnorePatterns in package.json to ignore files ending with .helper.ts and .helper.d.ts for cleaner test execution. * ci: update test mocks --------- Co-authored-by: Danny Avila <danny@librechat.ai>	2025-10-31 15:00:21 -04:00
Federico Ruggi	ea45d0b9c6	🏷️ fix: Add user ID to MCP tools cache keys (#10201) ... * add user id to mcp tools cache key * tests * clean up redundant tests * remove unused imports	2025-10-30 17:09:56 -04:00
Federico Ruggi	5ce67b5b71	📮 feat: Custom OAuth Headers Support for MCP Server Config (#10014) ... * add oauth_headers field to mcp options * wrap fetch to pass oauth headers * fix order * consolidate headers passing * fix tests	2025-10-11 11:17:12 -04:00
Danny Avila	4f3683fd9a	👤 fix: Missing User Placeholder Fields for MCP Services (#9824)	2025-09-24 22:48:38 -04:00
Sean McGrath	f61e057f7f	🔐 fix: MCP OAuth Token Persistence Race Condition and Refresh Auth Method (#9773) ... * set supported endpoint auth method when token_url exists * persist tokens immediately * add token storage validation tests	2025-09-23 09:35:56 -04:00
Danny Avila	5b1a31ef4d	🔄 refactor: Optimize MCP Tool Initialization ... 🔄 refactor: Optimize MCP Tool Initialization fix: update tool caching to use separated mcp logic refactor: Replace `req.user` with `userId` in MCP handling functions refactor: Replace `req` parameter with `userId` in file search tool functions fix: Update user connection parameter to use object format in reinitMCPServer refactor: Simplify MCP tool creation logic and improve handling of tool configurations to avoid capturing too much in closures refactor: ensure MCP available tools are fetched from cache only when needed	2025-09-21 20:31:28 -04:00
Danny Avila	386900fb4f	🧰 refactor: Decouple MCP Tools from System Tools (#9748)	2025-09-21 07:56:40 -04:00
Federico Ruggi	d04da60b3b	💫 feat: MCP OAuth Auto-Reconnect (#9646) ... * add oauth reconnect tracker * add connection tracker to mcp manager * reconnect oauth mcp servers function * call reconnection in auth controller * make sure to check connection in panel * wait for isConnected * add const for poll interval * add logging to tryReconnect * check expiration * check mcp manager is not null * check mcp manager is not null * add test for reconnecting mcp server * unify logic inside OAuthReconnectionManager * test reconnection manager, adjust * chore: reorder import statements in index.js * chore: imports * chore: imports * chore: imports * chore: imports * chore: imports * chore: imports and use types explicitly --------- Co-authored-by: Danny Avila <danny@librechat.ai>	2025-09-17 16:49:36 -04:00
Danny Avila	c827fdd10e	🚦 feat: Auto-reinitialize MCP Servers on Request (#9226)	2025-08-23 03:27:05 -04:00
Danny Avila	da4aa37493	🛠️ refactor: Consolidate MCP Tool Caching (#9172) ... * 🛠️ refactor: Consolidate MCP Tool Caching * 🐍 fix: Correctly mock and utilize updateMCPUserTools in MCP route tests	2025-08-20 12:19:29 -04:00
Theo N. Truong	8780a78165	♻️ refactor: MCPManager for Scalability, Fix App-Level Detection, Add Lazy Connections (#8930) ... * feat: MCP Connection management overhaul - Making MCPManager manageable Refactor the monolithic MCPManager into focused, single-responsibility classes: • MCPServersRegistry: Server configuration discovery and metadata management • UserConnectionManager: Manages user-level connections • ConnectionsRepository: Low-level connection pool with lazy loading • MCPConnectionFactory: Handles MCP connection creation with OAuth support New Features: • Lazy loading of app-level connections for horizontal scaling • Automatic reconnection for app-level connections • Enhanced OAuth detection with explicit requiresOAuth flag • Centralized MCP configuration management Bug Fixes: • App-level connection detection in MCPManager.callTool • MCP Connection Reinitialization route behavior Optimizations: • MCPConnection.isConnected() caching to reduce overhead • Concurrent server metadata retrieval instead of sequential This refactoring addresses scalability bottlenecks and improves reliability while maintaining backward compatibility with existing configurations. * feat: Enabled import order in eslint. * # Moved tests to __tests__ folder # added tests for MCPServersRegistry.ts * # Add unit tests for ConnectionsRepository functionality * # Add unit tests for MCPConnectionFactory functionality * # Reorganize MCP connection tests and improve error handling * # reordering imports * # Update testPathIgnorePatterns in jest.config.mjs to exclude development TypeScript files * # removed mcp/manager.ts	2025-08-13 11:45:06 -04:00
Dustin Healy	f1c6e4d55e	🧪 ci: Unit Tests for MCP Routes (#8803) ... * refactor: remove unreachable if checks from mcp routes * test: add tests for mcp routes	2025-08-01 14:47:00 -04:00
Danny Avila	32081245da	🪵 chore: Remove Unnecessary Comments	2025-07-29 14:59:58 -04:00
Dustin Healy	6fd3b569ac	⚒️ fix: MCP Initialization Flows (#8734) ... * fix: add OAuth flow back in to success state * feat: disable server clicks during initialization to prevent spam * fix: correct new tab behavior for OAuth between one-click and normal initialization flows * fix: stop polling on error during oauth (was infinite popping toasts because we didn't clear interval) * fix: cleanupServerState should be called after successful cancelOauth, not before * fix: change from completeFlow to failFlow to avoid stale client IDs on OAuth after cancellation * fix: add logic to differentiate between cancelled and failed flows when checking status for indicators (so error triangle indicator doesn't show up on cancellaiton)	2025-07-29 14:54:07 -04:00
Dustin Healy	c4677ab3fb	🔑 refactor: MCP Settings Rendering Logic for OAuth Servers (#8718) ... * feat: add OAuth servers to conditional rendering logic for MCPPanel in SideNav * feat: add startup flag check to conditional rendering logic * fix: correct improper handling of failure state in reinitialize endpoint * fix: change MCP config components to better handle servers without customUserVars - removes the subtle reinitialize button from config components of servers without customUserVars or OAuth - adds a placeholder message for components where servers have no customUserVars configured * style: swap CustomUserVarsSection and ServerInitializationSection positions * style: fix coloring for light mode and align more with existing design patterns * chore: remove extraneous comments * chore: reorder imports and `isEnabled` from api package --------- Co-authored-by: Danny Avila <danny@librechat.ai>	2025-07-29 09:08:46 -04:00
Dustin Healy	0ef3fefaec	🏹 feat: Concurrent MCP Initialization Support (#8677) ... * ✨ feat: Enhance MCP Connection Status Management - Introduced new functions to retrieve and manage connection status for multiple MCP servers, including OAuth flow checks and server-specific status retrieval. - Refactored the MCP connection status endpoints to support both all servers and individual server queries. - Replaced the old server initialization hook with a new `useMCPServerManager` hook for improved state management and handling of multiple OAuth flows. - Updated the MCPPanel component to utilize the new context provider for better state handling and UI updates. - Fixed a number of UI bugs when initializing servers * 🗣️ i18n: Remove unused strings from translation.json * refactor: move helper functions out of the route module into mcp service file * ci: add tests for newly added functions in mcp service file * fix: memoize setMCPValues to avoid render loop	2025-07-28 12:25:34 -04:00
Dustin Healy	545a909953	🗂️ refactor: Make MCPSubMenu consistent with MCPSelect (#8650) ... - Refactored MCPSelect and MCPSubMenu components to utilize a new custom hook, `useMCPServerManager`, for improved state management and server initialization logic. - Added functionality to handle simultaneous MCP server initialization requests, including cancellation and user notifications. - Updated translation files to include new messages for initialization cancellation. - Improved the configuration dialog handling for MCP servers, streamlining the user experience when managing server settings.	2025-07-25 14:51:42 -04:00
Danny Avila	74d8a3824c	🔌 feat: MCP Reinitialization and OAuth in UI (#8598) ... * ✨ feat: Add connection status endpoint for MCP servers - Implemented a new endpoint to retrieve the connection status of all MCP servers without disconnecting idle connections. - Enhanced MCPManager class with a method to get all user-specific connections. * feat: add silencer arg to loadCustomConfig function to conditionally print config details - Modified loadCustomConfig to accept a printConfig parameter that allows me to prevent the entire custom config being printed every time it is called * fix: new status endpoint actually works now, changes to manager.ts to support it - Updated the connection status endpoint to utilize Maps for app and user connections, rather than incorrectly treating them as objects. - Introduced a new method + variable in MCPManager to track servers requiring OAuth discovered at startup. - Stopped OAuth flow from continuing once detected during startup for a new connection * refactor: Remove hasAuthConfig since we can get that on the frontend without needing to use the endpoint * feat: Add MCP connection status query and query key for new endpoint - Introduced a new query hook `useMCPConnectionStatusQuery` to fetch the connection status of MCP servers. - Added request in data-service - Defined the API endpoint for retrieving MCP connection status in api-endpoints.ts. - Defined new types for MCP connection status responses in the types module. - Added mcpConnectionStatus key * feat: Enhance MCPSelect component with connection status and server configuration - Added connection status handling for MCP servers using the new `useMCPConnectionStatusQuery` hook. - Implemented logic to display appropriate status icons based on connection state and authentication configuration. - Updated the server selection logic to utilize configured MCP servers from the startup configuration. - Refactored the rendering of configuration buttons and status indicators for improved user interaction. * refactor: move MCPConfigDialog to its own MCP subdir in ui and update import * refactor: silence loadCustomConfig in status endpoint * feat: Add optional pluginKey parameter to getUserPluginAuthValue * feat: Add MCP authentication values endpoint and related queries - Implemented a new endpoint to check authentication value flags for specific MCP servers, returning boolean indicators for each custom user variable. - Added a corresponding query hook `useMCPAuthValuesQuery` to fetch authentication values from the frontend. - Defined the API endpoint for retrieving MCP authentication values in api-endpoints.ts. - Updated data-service to include a method for fetching MCP authentication values. - Introduced new types for MCP authentication values responses in the types module. - Added a new query key for MCP authentication values. * feat: Localize MCPSelect component status labels and aria attributes - Updated the MCPSelect component to use localized strings for connection status labels and aria attributes, enhancing accessibility and internationalization support. - Added new translation keys for various connection states in the translation.json file. * feat: Implement filtered MCP values selection based on connection status in MCPSelect - Added a new `filteredSetMCPValues` function to ensure only connected servers are selectable in the MCPSelect component. - Updated the rendering logic to visually indicate the connection status of servers by adjusting opacity. - Enhanced accessibility by localizing the aria-label for the configuration button. * feat: Add CustomUserVarsSection component for managing user variables - Introduced a new `CustomUserVarsSection` component to allow users to configure custom variables for MCP servers. - Integrated localization for user interface elements and added new translation keys for variable management. - Added functionality to save and revoke user variables, with visual indicators for set/unset states. * feat: Enhance MCPSelect and MCPConfigDialog with improved state management and UI updates - Integrated `useQueryClient` to refetch queries for tools, authentication values, and connection status upon successful plugin updates in MCPSelect. - Simplified plugin key handling by directly using the formatted plugin key in save and revoke operations. - Updated MCPConfigDialog to include server status indicators and improved dialog content structure for better user experience. - Added new translation key for active status in the localization files. * feat: Enhance MCPConfigDialog with dynamic server status badges and localization updates - Added a helper function to render status badges based on the connection state of the MCP server, improving user feedback on connection status. - Updated the localization files to include new translation keys for connection states such as "Connecting" and "Offline". - Refactored the dialog to utilize the new status rendering function for better code organization and readability. * feat: Implement OAuth handling and server initialization in MCP reinitialize flow - Added OAuth handling to the MCP reinitialize endpoint, allowing the server to capture and return OAuth URLs when required. - Updated the MCPConfigDialog to include a new ServerInitializationSection for managing server initialization and OAuth flow. - Enhanced the user experience by providing feedback on server status and OAuth requirements through localized messages. - Introduced new translation keys for OAuth-related messages in the localization files. - Refactored the MCPSelect component to remove unused authentication configuration props. * feat: Make OAuth actually work / update after OAuth link authorized - Improved the handling of OAuth flows in the MCP reinitialize process, allowing for immediate return when OAuth is initiated. - Updated the UserController to extract server names from plugin keys for better logging and connection management. - Enhanced the MCPSelect component to reflect authentication status based on OAuth requirements. - Implemented polling for OAuth completion in the ServerInitializationSection to improve user feedback during the connection process. - Refactored MCPManager to support new OAuth flow initiation logic and connection handling. * refactor: Simplify MCPPanel component and enhance server status display - Removed unused imports and state management related to user plugins and server reinitialization. - Integrated connection status handling directly into the MCPPanel for improved user feedback. - Updated the rendering logic to display server connection states with visual indicators. - Refactored the editing view to utilize new components for server initialization and custom user variables management. * chore: remove comments * chore: remove unused translation key for MCP panel * refactor: Rename returnOnOAuthInitiated to returnOnOAuth for clarity * refactor: attempt initialize on server click * feat: add cancel OAuth flow functionality and related UI updates * refactor: move server status icon logic into its own component * chore: remove old localization strings (makes more sense for icon labels to just use configure stirng since thats where it leads to) * fix: fix accessibility issues with MCPSelect * fix: add missing save/revoke mutation logic to MCPPanel * styling: add margin to checkmark in MultiSelect * fix: add back in customUserVars check to hide gear config icon for servers without customUserVars --------- Co-authored-by: Dustin Healy <dustinhealy1@gmail.com> Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>	2025-07-22 22:52:45 -04:00
Dustin Healy	faaba30af1	✨ feat: Add MCP Reinitialization to MCPPanel (#8418) ... * ✨ feat: Add MCP Reinitialization to MCPPanel - Refactored tool caching to include user-specific tools in various service files. - Refactored MCPManager class for clarity - Added a new endpoint for reinitializing MCP servers, allowing for dynamic updates of server configurations. - Enhanced the MCPPanel component to support server reinitialization with user feedback. * 🔃 refactor: Simplify Plugin Deduplication and Clear Cache Post-MCP Initialization - Replaced manual deduplication of tools with the dedicated `filterUniquePlugins` function for improved readability. - Added back cache clearing for tools after MCP initialization to ensure fresh data is used. - Removed unused exports from `PluginController.js` to clean up the codebase.	2025-07-21 17:49:19 -04:00
Danny Avila	ec7370dfe9	🪐 feat: MCP OAuth 2.0 Discovery Support (#7924) ... * chore: Update @modelcontextprotocol/sdk to version 1.12.3 in package.json and package-lock.json - Bump version of @modelcontextprotocol/sdk to 1.12.3 to incorporate recent updates. - Update dependencies for ajv and cross-spawn to their latest versions. - Add ajv as a new dependency in the sdk module. - Include json-schema-traverse as a new dependency in the sdk module. * feat: @librechat/auth * feat: Add crypto module exports to auth package - Introduced a new crypto module by creating index.ts in the crypto directory. - Updated the main index.ts of the auth package to export from the new crypto module. * feat: Update package dependencies and build scripts for auth package - Added @librechat/auth as a dependency in package.json and package-lock.json. - Updated build scripts to include the auth package in both frontend and bun build processes. - Removed unused mongoose and openid-client dependencies from package-lock.json for cleaner dependency management. * refactor: Migrate crypto utility functions to @librechat/auth - Replaced local crypto utility imports with the new @librechat/auth package across multiple files. - Removed the obsolete crypto.js file and its exports. - Updated relevant services and models to utilize the new encryption and decryption methods from @librechat/auth. * feat: Enhance OAuth token handling and update dependencies in auth package * chore: Remove Token model and TokenService due to restructuring of OAuth handling - Deleted the Token.js model and TokenService.js, which were responsible for managing OAuth tokens. - This change is part of a broader refactor to streamline OAuth token management and improve code organization. * refactor: imports from '@librechat/auth' to '@librechat/api' and add OAuth token handling functionality * refactor: Simplify logger usage in MCP and FlowStateManager classes * chore: fix imports * feat: Add OAuth configuration schema to MCP with token exchange method support * feat: FIRST PASS Implement MCP OAuth flow with token management and error handling - Added a new route for handling OAuth callbacks and token retrieval. - Integrated OAuth token storage and retrieval mechanisms. - Enhanced MCP connection to support automatic OAuth flow initiation on 401 errors. - Implemented dynamic client registration and metadata discovery for OAuth. - Updated MCPManager to manage OAuth tokens and handle authentication requirements. - Introduced comprehensive logging for OAuth processes and error handling. * refactor: Update MCPConnection and MCPManager to utilize new URL handling - Added a `url` property to MCPConnection for better URL management. - Refactored MCPManager to use the new `url` property instead of a deprecated method for OAuth handling. - Changed logging from info to debug level for flow manager and token methods initialization. - Improved comments for clarity on existing tokens and OAuth event listener setup. * refactor: Improve connection timeout error messages in MCPConnection and MCPManager and use initTimeout for connection - Updated the connection timeout error messages to include the duration of the timeout. - Introduced a configurable `connectTimeout` variable in both MCPConnection and MCPManager for better flexibility. * chore: cleanup MCP OAuth Token exchange handling; fix: erroneous use of flowsCache and remove verbose logs * refactor: Update MCPManager and MCPTokenStorage to use TokenMethods for token management - Removed direct token storage handling in MCPManager and replaced it with TokenMethods for better abstraction. - Refactored MCPTokenStorage methods to accept parameters for token operations, enhancing flexibility and readability. - Improved logging messages related to token persistence and retrieval processes. * refactor: Update MCP OAuth handling to use static methods and improve flow management - Refactored MCPOAuthHandler to utilize static methods for initiating and completing OAuth flows, enhancing clarity and reducing instance dependencies. - Updated MCPManager to pass flowManager explicitly to OAuth handling methods, improving flexibility in flow state management. - Enhanced comments and logging for better understanding of OAuth processes and flow state retrieval. * refactor: Integrate token methods into createMCPTool for enhanced token management * refactor: Change logging from info to debug level in MCPOAuthHandler for improved log management * chore: clean up logging * feat: first pass, auth URL from MCP OAuth flow * chore: Improve logging format for OAuth authentication URL display * chore: cleanup mcp manager comments * feat: add connection reconnection logic in MCPManager * refactor: reorganize token storage handling in MCP - Moved token storage logic from MCPManager to a new MCPTokenStorage class for better separation of concerns. - Updated imports to reflect the new token storage structure. - Enhanced methods for storing, retrieving, updating, and deleting OAuth tokens, improving overall token management. * chore: update comment for SYSTEM_USER_ID in MCPManager for clarity * feat: implement refresh token functionality in MCP - Added refresh token handling in MCPManager to support token renewal for both app-level and user-specific connections. - Introduced a refreshTokens function to facilitate token refresh logic. - Enhanced MCPTokenStorage to manage client information and refresh token processes. - Updated logging for better traceability during token operations. * chore: cleanup @librechat/auth * feat: implement MCP server initialization in a separate service - Added a new service to handle the initialization of MCP servers, improving code organization and readability. - Refactored the server startup logic to utilize the new initializeMCP function. - Removed redundant MCP initialization code from the main server file. * fix: don't log auth url for user connections * feat: enhance OAuth flow with success and error handling components - Updated OAuth callback routes to redirect to new success and error pages instead of sending status messages. - Introduced `OAuthSuccess` and `OAuthError` components to provide user feedback during authentication. - Added localization support for success and error messages in the translation files. - Implemented countdown functionality in the success component for a better user experience. * fix: refresh token handling for user connections, add missing URL and methods - add standard enum for system user id and helper for determining app-lvel vs. user-level connections * refactor: update token handling in MCPManager and MCPTokenStorage * fix: improve error logging in OAuth authentication handler * fix: concurrency issues for both login url emission and concurrency of oauth flows for shared flows (same user, same server, multiple calls for same server) * fix: properly fail shared flows for concurrent server calls and prevent duplication of tokens * chore: remove unused auth package directory from update configuration * ci: fix mocks in samlStrategy tests * ci: add mcpConfig to AppService test setup * chore: remove obsolete MCP OAuth implementation documentation * fix: update build script for API to use correct command * chore: bump version of @librechat/api to 1.2.4 * fix: update abort signal handling in createMCPTool function * fix: add optional clientInfo parameter to refreshTokensFunction metadata * refactor: replace app.locals.availableTools with getCachedTools in multiple services and controllers for improved tool management * fix: concurrent refresh token handling issue * refactor: add signal parameter to getUserConnection method for improved abort handling * chore: JSDoc typing for `loadEphemeralAgent` * refactor: update isConnectionActive method to use destructured parameters for improved readability * feat: implement caching for MCP tools to handle app-level disconnects for loading list of tools * ci: fix agent test	2025-06-17 13:50:33 -04:00