LibreChat/api/server/routes/mcp.js
Danny Avila fa913148fb
🔒 fix: Refresh MCP OBO Tokens From the Live OpenID Session (#15334)
* 🧊 fix: Inline-refresh OpenID session tokens at MCP OBO call time

Resolves the walk-away failure mode where MCP tool calls using OBO auth
fail with "No valid OpenID access token is available for OBO exchange"
after a user idles past their access-token lifetime. The strategy-time
snapshot on `user.federatedTokens` could expire mid-stream before
`resolveOboToken` ran, while `req.session.openidTokens` carried a still-
valid (or refreshable) token that nothing read.

- New OpenIDSessionRefresh service: per-user single-flighted closure that
  reads `req.session.openidTokens` at OBO time and inline-refreshes via
  `openid-client.refreshTokenGrant` when expired (30s skew), persisting
  via `req.session.save()`. No cookie writes (headers already flushed).
- `resolveOboToken` gains a required UpstreamTokenProvider parameter
  (typed as `() => Promise<OIDCTokens | null>`, reusing the shared shape
  from @librechat/data-schemas). Compile-time guarantee that every call
  site is updated.
- New `session_refresh_failed` OboTokenResolutionReason distinguishes
  "session expired and IdP rejected refresh" from "no upstream token
  ever existed."
- `req` threaded through createMCPTool/createMCPTools/createToolInstance
  to construct the closure with captured request, plus fail-closed
  guards in MCPConnectionFactory.getOboTokens and MCPManager.callTool
  when the closure isn't plumbed.
- Startup warning in MCPServersInitializer when OBO is configured but
  OPENID_REUSE_TOKENS is unset (the strategy populating
  user.federatedTokens is only registered under reuse, so OBO would
  fail every call without it).

Tests: 16 new in OpenIDSessionRefresh.spec.js; obo.spec.ts extended
for the new param + error reason; wiring smoke tests in MCPManager,
MCPConnectionFactory, MCPServersInitializer, and MCP.spec.js.

* 🛡️ fix: Harden OBO inline-refresh against token type and session edge cases

- Token-preference asymmetry: live-token reuse and expires_at derivation
  now strictly gate on the access_token, not the id_token. Added a
  required `tokenPreference` parameter on isLiveSessionTokenStillValid,
  buildOIDCTokensFromSession, and createOpenIDSessionTokenProvider
  so every call site is explicit. Dropped the bogus id_token-exp
  fallback in performIdpRefresh — id_token TTL is governed by IdP
  session policy and would mark a short-lived access_token reusable
  past its real lifetime.
- Missing req in /reinitialize route: the manual reconnect
  endpoint now forwards req into reinitMCPServer, so OBO servers can
  build a session-aware upstream-token closure instead of failing with
  missing_upstream_token.
- Single-flight key collisions: composed key as
  tenantId:openidIssuer:openidId:sessionId via getSingleFlightKey.
  Concurrent calls in the same session still coalesce; separate sessions
  never share an in-flight refresh, preventing refresh-token rotation
  from breaking sibling sessions and preventing cross-tenant token
  crossover when distinct users share an IdP sub.
- Opaque access token reuse): persist accessTokenExpiresAt
  (unix seconds, from tokenset.expires_in) on each refresh AND on initial
  login / SPA refresh in setOpenIDAuthTokens. New getAccessTokenExp
  helper falls back to it when the access token isn't a JWT, avoiding
  redundant inline refreshes for Microsoft Graph and Auth0 default
  audiences.
- Log hygiene: the single-flight key (containing sessionId,
  openidId, openidIssuer, tenantId) is now SHA-256-hashed in the
  "Joining in-flight refresh" debug log. Preserves cross-line correlation
  via a 12-char prefix without leaking credential or PII material.

Documented req.session.openidTokens shape contract via JSDoc typedef so
the new accessTokenExpiresAt field has a discoverable home alongside the
existing accessToken/idToken/refreshToken/expiresAt/lastRefreshedAt.

Tests: OpenIDSessionRefresh.spec.js up to 30 passing (added coverage for
opaque-token reuse, JWT-access-token-exp fallback, no-id_token-fallback
regression, cross-session no-coalesce, persistence on refresh, and a
guard against stale accessTokenExpiresAt carryover). AuthService.spec.js
adds two cases covering accessTokenExpiresAt persistence on login.
mcp.spec.js (route) gains a regression test asserting req flows into
reinitMCPServer.

* 🔍 fix: Detect OBO-only MCP admin config overrides

Admin Config overlays for YAML-defined MCP servers compare only
ADMIN_CONFIGURABLE_FIELDS to decide whether to lazy-init a config-tier override.
The OBO config field was added after that fingerprint list, so an override that
only added or changed `obo` was treated as unchanged YAML and skipped.

Include `obo` in the admin-configurable field list and add a regression test for
an OBO-only override.

* 🔊 fix: Mock MCP OAuth timeout in SDK integration test

MCPConnectionFactory.attemptToConnect reads mcpConfig.OAUTH_HANDLING_TIMEOUT
when building the OAuth connection timeout. The SDK OAuth integration test
mocked mcpConfig without that field, which made the timeout calculation produce
NaN and caused the test to fail before the OAuth refresh/start path completed.

Add OAUTH_HANDLING_TIMEOUT to the test mock.

* ♻️ refactor: Pass OBO upstream-token closure into MCP instead of req

Build the OpenID upstream-token provider at the request boundary and thread
only the closure through MCP handling, so the MCP service layer no longer
receives the raw Express request. The closure still reads/refreshes the live
session at tool-call time, preserving the walk-away recovery.

- Drop `req`/`capturedReq` from createMCPTools, createMCPTool, reconnectServer,
  createToolInstance, and reinitMCPServer; forward `upstreamTokenProvider`
  instead. Closure is constructed in loadTools, loadToolDefinitionsWrapper, and
  the reinitialize route, where req/res are in scope.
- OBO: fall back to user.federatedTokens when the provider yields no live
  session, so OIDC remote-agent calls (verified bearer, no session) still work.
- Inline refresh: mirror a rotated refresh token to the refreshToken cookie via
  a shared setRefreshTokenCookie helper, guarded by !res.headersSent (no-op on
  the streaming path; session copy stays authoritative).
- Single-flight: hydrate a joining request's own session from the resolved
  tokens so a later OBO call doesn't replay a rotated-away refresh token.

Addresses owner feedback and three review findings.

* 🔒 fix: Recover OIDC refresh-token rotation after SSE OBO refresh

When an inline OBO refresh rotates the OpenID refresh token after SSE headers
have already been sent, the browser refreshToken cookie cannot be updated. Store
a short-lived encrypted bridge from the stale cookie token to the rotated token
so /api/auth/refresh can recover after express-session loss.

Use the signed openid_user_id cookie to load user context for bridge validation,
retry only on invalid_grant, and delete the bridge only after the bridged refresh
succeeds.

* 🔨 fix: hydrate joined OIDC refresh sessions with stable refresh tokens

Update single-flight OIDC refresh joiners whenever refreshed access token
state changes, even if the IdP keeps the refresh token unchanged.

This prevents joined requests from retaining stale accessToken or
accessTokenExpiresAt values and redundantly refreshing later in the same run.

* 🌉 Persist OIDC refresh-token recovery bridges in MongoDB

Store SSE OBO refresh-token recovery bridges in MongoDB instead of
process-local memory so /api/auth/refresh can recover after worker
restarts or cross-worker routing.

Derive bridge expiry from REFRESH_TOKEN_EXPIRY so the recovery window
matches the stale refreshToken cookie it repairs, and delete bridges
after successful recovery.

* 🤝 Coordinate OIDC inline refreshes across workers

Add a short-lived Mongo-backed refresh-flight record so concurrent
OBO refreshes for the same OpenID session do not redeem the same
rotating refresh token on different workers.

The winning worker performs the IdP refresh and stores an encrypted
result; joiners wait for that result, hydrate their request session,
and return without calling the IdP.

*  Keep OpenID marker cookies aligned on inline refresh

Refresh token_provider and openid_user_id with the same expiry as the
rotated refreshToken cookie when an inline OBO refresh can still write
headers.

Share the marker-cookie writer with the normal OpenID auth refresh path
so the fallback /api/auth/refresh branch continues to recognize valid
OpenID refresh tokens after session expiry.

* 🔑 fix: include refresh token in OIDC local refresh flight key

Key the process-local OIDC refresh coalescing by the current session
refresh token, matching the Mongo-backed flight key. This prevents a
request with a newly rotated token from joining an older pending refresh
and inheriting its failure/result.

* 🌉 fix: store OIDC refresh bridge without cookie response

Treat missing or non-cookie responses like headers-sent streaming
responses during inline OIDC refresh. When the IdP rotates the refresh
token and cookies cannot be written, persist a recovery bridge so a later
/auth/refresh can recover after session expiry.

* 🫙 fix: preserve stale OIDC cookie bridge key

Track the refresh token last written to the browser cookie separately
from the current session refresh token. When inline OIDC refreshes rotate
tokens without a writable response, keep bridging from the browser-stale
token directly to the latest session token.

* 🙌 fix: keep OIDC bridge recovery success on cleanup failure

Make refresh-token bridge cleanup best-effort after a bridged OIDC
refresh succeeds. A transient delete failure now logs a warning but does
not convert the already-refreshed session and cookies into a 403 response.

* 📦 test: Exclude RefreshTokenBridge from tenant-isolation coverage

Add RefreshTokenBridge to the tenant-isolation coverage allowlist because
refresh bridge lookups run during unauthenticated OpenID refresh recovery.
The controller first recovers user context from the signed OpenID marker
cookie, then the bridge methods apply explicit user and tenant filters.

Ambient tenant isolation would bind this recovery path to request-local
tenant context that is not available at the point the stale cookie is being
resolved

*  Fix OpenID refresh flight retry and marker hydration

Allow failed OpenID refresh flights to be reclaimed immediately instead of pinning transient errors.

Preserve the browser refresh-token marker when joined refreshes hydrate session tokens from a shared flight result.

Stabilize AuthService tests by isolating mocked module imports from prior suites.

* 🛠️ fix: centralize OBO identity scoping

Add shared auth identity helpers for app user ids, OpenID subjects,
tenant ids, and normalized OpenID issuers.

Thread a non-placeholder-visible OBO identity context from the real
request user through MCP connection, tool-call, reinit, and refresh
paths. Keep tenantId and openidIssuer out of createSafeUser so MCP
user placeholders do not expose those fields.

Scope OBO token cache and in-flight exchange keys by tenant, issuer,
OpenID subject, scopes, and a SHA-256 hash of the upstream assertion.
This prevents cross-tenant/cross-issuer collisions and avoids reusing
tokens minted from stale rotated assertions.

Use the shared identity helpers for OpenID refresh-flight keys and
refresh-token bridge recovery records so related OBO refresh paths share
the same identity normalization rules.

The helper is intended for auth-boundary and credential-cache code, not
as a blanket replacement for ordinary app user id ownership checks.

* 🛠️ fix: preserve OIDC refresh-token sync on save failures

Sync OpenID refresh-token cookie/bridge state before persisting the
session so a transient session-store failure cannot lose an IdP-rotated
refresh token.

Also trigger sync when the session refresh token differs from the
browser refresh-token marker, not only when the current grant rotates
the token. This lets later writable refreshes repair stale browser
cookies left behind by SSE refreshes.

Route refresh bridge identity through the shared identity helper with
the threaded OBO identity context, falling back to request/user context
when needed.

Add regression coverage for session-save failures, stale browser cookie
repair, non-writable bridge storage, and shared-helper identity fallback.

* 🛠️ fix: keep OIDC refresh bridge during recovery grace

After successful bridged refresh recovery, re-store the stale-cookie bridge
with a short grace TTL instead of deleting it immediately. This lets parallel
/api/auth/refresh requests that already sent the stale browser cookie recover
before they can observe the first response's Set-Cookie.

Retarget the bridge to the refresh token returned by the bridged retry so
B-to-C refresh-token rotation remains recoverable. The grace TTL is parsed with
math() and defaults to 60s, which shrinks the replay window from the original
REFRESH_TOKEN_EXPIRY bridge lifetime to the short recovery grace period.

Remove the now-unused explicit bridge delete path from the service and
data-schemas method surface. Add regression coverage for grace re-store,
identity symmetry, retry failure behavior, and same-key upsert replacement.

* 🛠️ fix: fail closed on OBO MCP user identity mismatch

Add an OBO-specific guard before MCP tool execution that requires the
effective invocation user and captured request user to both have ids and
to match. This prevents OBO tool calls from falling back to a separate
configurable.user_id identity after request-bound OBO context has already
been captured.

Keep the existing user id fallback behavior for non-OBO MCP calls.

Tests cover mismatched OBO users, missing user ids, and the matching-user
path ignoring a conflicting configurable.user_id.

* 🛠️ fix: Guard OpenID bridge retry user identity

Extract the shared OpenID refresh/user-resolution flow in AuthController
so the normal refresh path and bridge-recovery retry use the same grant,
claims, issuer, user lookup, and diagnostic logging code.

Preserve the existing path-specific behavior: the normal path still owns
migration updates and 401 login redirects, while the bridge retry still
falls through to the existing 403 invalid-token response.

Add a bridge-recovery guard that rejects retry results whose resolved
user id differs from the signed openid_user_id cookie before issuing
tokens or re-storing the grace bridge. Cover both the successful
matching-user recovery and the mismatched-user rejection.

* 🛠️ fix: type-safety polish on OBO data layer

Replace refresh token bridge query/update Record<string, unknown> usage
with typed Mongoose FilterQuery and UpdateQuery definitions.

Harden OpenID marker cookie JWT expiry handling by converting refresh
expiry milliseconds to integer seconds and rejecting invalid or
non-positive durations.

Add focused CSRF tests for fractional refresh expiry values and invalid
expiry configuration.

* 🛠️ fix: Bind OpenID session tokens to authenticated identity

Stamp OpenID session token state with the LibreChat user id, OpenID subject,
tenant id, and normalized issuer when tokens are stored.

Fail closed before OBO inline token reuse/refresh when the session token
identity does not match the current authenticated identity, preventing a stale
or mixed Express session from supplying another user's upstream assertion.

Also validate the normal /api/auth/refresh session-token reuse shortcut against
the signed marker-cookie user before returning cached session tokens.

Note: sessions created before this change carry no identity stamp and are
treated as a mismatch. This is self-healing — the reuse path forces a full IdP
refresh (which re-stamps the session) and the OBO path throws, surfacing as a
one-time re-authentication for active OBO users at deploy time. The session
re-stamps within one session lifetime (SESSION_EXPIRY, default 15 min).

* 🛠️ fix: Recover OpenID refresh token drift

Prefer the browser refresh-token cookie when it differs from the
server-side OpenID session state, and force a real IdP refresh in that
case instead of reusing stale session tokens.

Store a short-lived refresh-token bridge when inline OBO refresh writes
a rotated browser cookie but session persistence fails, so follow-up
refreshes can still recover from the old token.

Keep the bridge grace TTL centralized in RefreshTokenBridge so both
recovery paths use the same env-backed value.

Note: drift is measured against the last-synced browserRefreshToken
marker, so the SSE path (intentionally stale cookie, authoritative
session) does not false-positive. Sessions predating the marker have no
browserRefreshToken; for those, drift falls back to comparing the cookie
against the session refresh token and prefers the cookie on difference.
This is the same self-healing pre-change-session window as the identity
binding fix and re-syncs within one session lifetime.

Tests cover cookie/session drift selection, reusable-session bypass on
drift, bridge storage after session-save failure, and the shared bridge
constant wiring.

* 🛠️ fix: Harden OBO token caching and expiry handling

Reject malformed OBO grant responses before writing them to the exchanged-token cache so a missing access_token cannot poison the cache.

Store absolute expires_at values with cached OBO tokens and ignore legacy cache entries without usable expiry metadata. This keeps cached-token freshness based on the token’s real
remaining lifetime instead of reusing the original relative expires_in on cache hits.

Move OBO expiry normalization and skew helpers into packages/api and use them from both the JS exchange service and the TS MCP resolver. Apply a 30-second safety margin with a one-
second floor for short-lived tokens, covered by direct helper tests and caller-level regression tests.

Tests:
- packages/api: npm run build
- packages/api: npx jest src/mcp/oauth/expiry.spec.ts src/mcp/oauth/obo.spec.ts
- api: npx jest server/services/OboTokenService.spec.js

* 🛠️ fix: Harden OBO refresh-token bridge lookup and indexing

Reuse getValidOpenIDReuseUserId for the bridge-recovery user lookup in
refreshController instead of re-verifying openid_user_id inline. The shared
helper enforces the JWT_REFRESH_SECRET presence check and a strict
typeof payload.id === 'string' guard, rejecting tokens whose id claim is
present but not a string (e.g. a numeric id) that the inline check accepted.

Fail closed on issuer mismatch in getRefreshTokenBridge. Both the stored and
the expected issuer are now normalized and compared for equality, so a bridge
is recovered only when both sides agree (both absent, or both present and
equal after normalization). Previously the check was skipped whenever the
stored issuer was absent, allowing recovery across mismatched issuer context.

Drop the unused {oldRefreshTokenHash, userId, tenantId, openidIssuer} index
and the openidIssuer field on RefreshTokenBridgeQuery. The data-layer filter
only queries the 3-field {oldRefreshTokenHash, userId, tenantId} index; the
issuer is verified in application code, not the query. Hoist the repeated
model accessor into getRefreshTokenBridgeModel.

Note: issuer is now load-bearing for recovery. A bridge stored with an issuer
recovers only when the lookup supplies a matching issuer; the recovery lookup
reads user.openidIssuer via AUTH_REFRESH_USER_PROJECTION (an exclusion
projection that retains the field). If a user's persisted openidIssuer is
empty while the stored bridge has one, recovery fails closed (falls through to
normal re-authentication) until the bridge TTLs out — no security regression.

Tests cover invalid signed-cookie payloads bypassing the bridge, both
asymmetric issuer-presence cases, issuer normalization before comparison, and
an index-alignment assertion guarding against re-adding the dropped index.

* 🛠️ fix: Degrade OBO discovery on token resolution failures

Catch expected OboTokenResolutionError failures during MCP tool discovery and
fall back to unauthenticated tool listing instead of aborting discovery. This
keeps discovery aligned with the existing unauthenticated listing behavior while
preserving unexpected errors as real failures.

Also correct OBO tool-call freshness comment and tighten the OBO trust-check
permissions type to the existing role permission shape.

Tests:
- npx jest src/mcp/__tests__/MCPConnectionFactory.test.ts --runInBand --coverage=false
- npx jest src/mcp/oauth/obo.spec.ts --runInBand --coverage=false

* 🛠️ fix: tighten OBO tool-call errors, bridge logging, and flight typing

Move resolveToolCallUserId inside the tool-call try/catch so an OBO
identity mismatch surfaces with serverName/toolName context and the
standard tool-call-failed message instead of an opaque bare Error.

Raise the refresh-token bridge lookup failure log from debug to warn so
transient infrastructure failures on the unauthenticated /api/auth/refresh
path are observable, and guard the message access against non-Error values.

Replace the unknown+cast in isDuplicateKeyError with a hasErrorCode type
predicate so the duplicate-key check reads error.code without an assertion.

Preserve real math/isEnabled in the MCPConnectionFactory test mock (mock
only processMCPEnv) so mcpConfig timeouts no longer resolve to NaN, fixing
the TimeoutNaNWarning that masked slow OAuth retry behavior.

* 🧪 fix: Restore the Flight Uniqueness Index and Buffer the Graph Cache TTL

Two CI failures on the merge, both in suites this environment cannot run
(their MongoDB binary download is blocked).

`GraphApiService.spec.js` still asserted the unbuffered TTL. Graph tokens
route through the same `getTokenCacheTtlMs` as the OBO and openidStrategy
caches, so the entry now expires 30s before the credential does.

`openidRefreshFlight.spec.ts` dropped the database between tests, which takes
the indexes with it, and Mongoose builds them only once when the model is
compiled. Whether the unique `key` index survived into a test was a race with
that one-time build. Without it a second `create` inserts instead of raising a
duplicate-key error, so every worker believes it won the flight — the
mutual exclusion the file exists to prove. Indexes are now rebuilt after each
drop, which also makes the reclaim and complete cases reach those paths for
the right reason.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SxKWxwqxAGckYpRsYTqx3F

* fix: address OBO review findings

* 🔐 fix: Install Bridge Indexes and Carry OBO Through Assistant Recovery

Two findings from the Codex pass on d08c82f0d.

The refresh-token bridge relied on Mongoose auto-indexing for both of its
indexes, and `MONGO_AUTO_INDEX=false` is a supported deployment setting. A
bridge holds an encrypted refresh token and the TTL index is the only thing
that ever deletes one, so under that setting they would accumulate for the
life of the collection while concurrent upserts lost the compound uniqueness
the filter assumes. Installed before the first write, matching the flight
methods and the session and schedule methods before them.

`recoverServerTools`, the assistant create/update path that reruns
`reinitMCPServer` when a referenced server's catalog and connection snapshot
are both missing, was the last reinit site not carrying the upstream-token
closure. For an OBO server the factory rejects the connection outright, so the
assistant write failed with unavailable MCP definitions. It now builds the
provider at that request boundary like the other entry points; assistant
writes have no `res`, so a rotation there falls back to the recovery bridge.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SxKWxwqxAGckYpRsYTqx3F

* fix: harden OBO refresh coordination

*  fix: Keep Elapsed Expiries Elapsed and Revoke the Superseded Session

Two of the five findings from the Codex pass on fcdc15885 — the two that are
defects in code this branch introduced rather than design questions about the
bridge.

`getSkewedTokenExpiresAtMs` floored every result at a second in the future,
including an expiry the provider had already declared elapsed. An exchange
answering `expires_in: 0` or a past `expires_at` was handed to the MCP
connection stamped valid for another second, which only moves the failure
downstream. The floor now applies to a lifetime that is still live, which is
what it was for; an elapsed one stays elapsed so the caller rejects it. Same
for the cache TTL, which falls back to the elapsed-credential floor.

Bridge recovery left the stale token's durable Session behind. Only the token
it recovered through was passed as `existingRefreshToken`, so that one's
session was replaced while the token the browser actually presented kept its
record until its original expiry. That record, with the marker cookie still
bound to it, is what authorizes local image access for OpenID users — so a
copy of the stale cookie outlived the rotation it had lost. Revoked
explicitly on successful recovery.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SxKWxwqxAGckYpRsYTqx3F

* fix: close OBO refresh review findings

* 🎟️ fix: Carry the Bridged Token Through a Non-Rotating Recovery

Bridge recovery passes the browser's stale token as `existingRefreshToken` so
the durable Session naming it is the record replaced. That also makes the
stale token the fallback the installed session and the refresh cookie use when
a tokenset carries no `refresh_token` of its own, which holds only while the
recovery grant rotates.

An IdP that answers that grant without rotating sends the browser back to the
very token the bridge exists to retire: `storeOpenIDSession` installs and
deletes the same stale record in one call, and the cookie is rewritten to a
token the IdP already rejected — a sign-out on the next refresh. The grace
bridge one line above already guards this with `|| bridgedRefreshToken`; the
resolved tokenset now does the same, so leader and followers alike publish the
recovered token.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SxKWxwqxAGckYpRsYTqx3F

* 🚫 fix: Reject an OBO Exchange That Returns an Expired Credential

Preserving an elapsed expiry through the skew helper only helps if something
acts on it, and nothing did: `MCPManager.callTool` checks the access token and
nothing else before setting the Authorization header, so a credential the IdP
declared spent still went downstream to fail there. It is rejected at the
exchange now, where the reason is known, and retryably — the exchange itself
worked, so a fresh grant can succeed.

Completes the elapsed-expiry change in cb26a6f7d, which made the stamp honest
without giving anyone a reason to look at it.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SxKWxwqxAGckYpRsYTqx3F

* fix: close OpenID refresh review findings

* fix: coordinate OpenID refresh entry points

* chore: sort OpenID flight imports

* fix: fence OpenID refreshes during logout

* fix: close OpenID logout publication races

* fix: narrow completed refresh flight

* test: cover bridge cleanup failure after ownership loss

The compensating delete in storeRefreshTokenBridgeWithLease swallows its own
failure so the lease error stays the one the caller sees. Nothing asserted
that, so removing the inner catch left every suite green while callers began
receiving the cleanup error instead.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SxKWxwqxAGckYpRsYTqx3F

* fix: compensate OpenID bridges only on proven ownership loss

The post-write lease assertion deletes the bridge it just published when it
throws, but it threw for two different reasons: a coordination record that is
no longer ours, and a coordination read that simply failed. Treating the second
as the first destroys the only mapping from the token the browser still holds
to the one the IdP already rotated to, so a transient Mongo error on the
headers-already-sent path signed the user out.

Tag the ownership error where the lease raises it and compensate only for that,
preserving the bridge whenever ownership is merely undetermined. A preserved
bridge stays behind the logout revocation fence, so the safe default costs
nothing.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SxKWxwqxAGckYpRsYTqx3F

* fix: reject spent OpenID refresh results

Two ways a refresh could report success while handing back a credential
nothing can use.

An inline refresh carries the previous id_token forward when the IdP omits
one on rotation, so tokenset.id_token is not necessarily freshly issued.
setOpenIDAuthTokens applied its freshness guard only to the session copy and
took tokenset.id_token unconditionally, so /refresh returned an expired
bearer even though the grant produced a usable access token. Skip it only
when it is provably expired: an id_token whose expiry cannot be read stays
preferred, since access_token may be opaque or scoped to another audience.

normalizeExpiresIn preserves a zero or negative lifetime rather than
discarding it, so a grant declaring an already-spent access token still
published, rotating the refresh token and returning a token every freshness
check rejects. Each OBO call then repeated the grant. Reject an elapsed
lifetime before publishing; an unknown lifetime still publishes.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SxKWxwqxAGckYpRsYTqx3F

* fix: harden OpenID refresh publication

* fix: keep identity and results intact through OpenID refresh cleanup

Two follow-ons from the last round's fixes.

Stripping an expired carried-forward id_token from the refresh result removed
the only identity material a rotation without id_token leaves behind. The
result is rebuilt by buildOIDCTokensFromSession, so it carries no provider
claims() either, and getTokenClaims accepts only those two — bridge recovery
failed with "no usable identity claims" before setOpenIDAuthTokens could hand
back the fresh access token. The stripped token now travels in a
non-enumerable marker, alongside the existing browser and predecessor markers,
which identity resolution reads and the authentication response never sees.

The lease drained a pending renewal by awaiting it in finally, so a transient
coordination failure there threw from finally and replaced the operation's
result. The refresh had already settled and published, so the caller saw a
failure on credentials that had rotated. Proven ownership loss is recorded on
ownershipLost and checked before the return, so the drain has nothing to add
but noise; it now absorbs and logs.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SxKWxwqxAGckYpRsYTqx3F

* refactor: fence OpenID recovery publication

* fix: close OpenID publication transaction

* refactor: make OpenID publication transactional

* fix: satisfy OpenID publication type checks

* fix: fence OpenID session publication

* fix: authorize OpenID refresh publication

* fix: bind OpenID replay generations

* fix: fence OpenID response generations

* fix: authorize OpenID token delivery

* fix: linearize OpenID publication delivery

* chore: sort OpenID refresh flight imports

---------

Co-authored-by: J.C. Bartle <jcbartle@users.noreply.github.com>
Co-authored-by: jbartle <jbartle@rand.org>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: jcbartle <7274202+jcbartle@users.noreply.github.com>
2026-08-29 23:55:58 -04:00

1162 lines
39 KiB
JavaScript

const { Router } = require('express');
const { logger, getTenantId, tenantStorage } = require('@librechat/data-schemas');
const {
CacheKeys,
Constants,
Permissions,
PermissionBits,
PermissionTypes,
} = require('librechat-data-provider');
const {
getBasePath,
createSafeUser,
createAuthIdentityContext,
MCPOAuthHandler,
MCPTokenStorage,
setOAuthSession,
PENDING_STALE_MS,
getUserMCPAuthMap,
validateOAuthCsrf,
OAUTH_CSRF_COOKIE,
setOAuthCsrfCookie,
generateCheckAccess,
validateOAuthSession,
OAUTH_SESSION_COOKIE,
mcpConfig: mcpSettings,
getServerCustomUserVars,
hasCustomUserVars,
requiresEphemeralUserConnection,
} = require('@librechat/api');
const {
createMCPServerController,
updateMCPServerController,
deleteMCPServerController,
getMCPServersList,
getMCPServerById,
getMCPTools,
} = require('~/server/controllers/mcp');
const {
getOAuthReconnectionManager,
getMCPServersRegistry,
getFlowStateManager,
getMCPManager,
} = require('~/config');
const {
getServerConnectionStatus,
resolveAllMcpConfigs,
resolveConfigServers,
getMCPSetupData,
} = require('~/server/services/MCP');
const { requireJwtAuth, canAccessMCPServerResource } = require('~/server/middleware');
const { getUserPluginAuthValue } = require('~/server/services/PluginService');
const { invalidateCachedTools } = require('~/server/services/Config');
const { updateMCPServerTools } = require('~/server/services/Config/mcp');
const { reinitMCPServer } = require('~/server/services/Tools/mcp');
const { createOpenIDSessionTokenProvider } = require('~/server/services/OpenIDSessionRefresh');
const { getLogStores } = require('~/cache');
const db = require('~/models');
const router = Router();
const OAUTH_CSRF_COOKIE_PATH = '/api/mcp';
const getOAuthFlowId = (userId, serverName) =>
MCPOAuthHandler.generateFlowId(userId, serverName, getTenantId());
const canAccessOAuthFlow = (flowId, userId) => {
const parsed = MCPOAuthHandler.parseFlowId(flowId);
if (!parsed) {
return false;
}
if (parsed.tenantId && parsed.tenantId !== getTenantId()) {
return false;
}
return parsed.userId === userId || parsed.userId === 'system';
};
const clearGetTokensFlow = async ({ flowManager, flowId, tokens }) => {
const state = await flowManager.getFlowState(flowId, 'mcp_get_tokens');
if (state?.type === 'mcp_get_tokens' && state.status === 'PENDING') {
await flowManager.completeFlow(flowId, 'mcp_get_tokens', tokens);
return;
}
await flowManager.deleteFlow(flowId, 'mcp_get_tokens');
};
const checkMCPUsePermissions = generateCheckAccess({
permissionType: PermissionTypes.MCP_SERVERS,
permissions: [Permissions.USE],
getRoleByName: db.getRoleByName,
});
const checkMCPCreate = generateCheckAccess({
permissionType: PermissionTypes.MCP_SERVERS,
permissions: [Permissions.USE, Permissions.CREATE],
getRoleByName: db.getRoleByName,
});
/**
* Get all MCP tools available to the user
* Returns only MCP tools, completely decoupled from regular LibreChat tools
*/
router.get('/tools', requireJwtAuth, checkMCPUsePermissions, async (req, res) => {
return getMCPTools(req, res);
});
/**
* Initiate OAuth flow
* This endpoint is called when the user clicks the auth link in the UI
*/
router.get('/:serverName/oauth/initiate', requireJwtAuth, setOAuthSession, async (req, res) => {
try {
const { serverName } = req.params;
const { userId, flowId } = req.query;
const user = req.user;
// Verify the userId matches the authenticated user
if (typeof userId !== 'string' || userId !== user.id) {
return res.status(403).json({ error: 'User mismatch' });
}
const expectedFlowId = getOAuthFlowId(user.id, serverName);
if (typeof flowId !== 'string' || flowId !== expectedFlowId) {
logger.error('[MCP OAuth] Invalid flow ID for initiate request', {
serverName,
userId,
flowId,
expectedFlowId,
});
return res.status(403).json({ error: 'Flow mismatch' });
}
logger.debug('[MCP OAuth] Initiate request', { serverName, userId, flowId });
const flowsCache = getLogStores(CacheKeys.FLOWS);
const flowManager = getFlowStateManager(flowsCache);
/** Flow state to retrieve OAuth config */
const flowState = await flowManager.getFlowState(flowId, 'mcp_oauth');
if (!flowState) {
logger.error('[MCP OAuth] Flow state not found', { flowId });
return res.status(404).json({ error: 'Flow not found' });
}
const {
authorizationUrl: storedAuthorizationUrl,
serverName: flowServerName,
userId: flowUserId,
serverUrl,
oauth: oauthConfig,
} = flowState.metadata || {};
if (flowUserId && flowUserId !== user.id) {
logger.error('[MCP OAuth] Flow user mismatch', { flowId, userId, flowUserId });
return res.status(403).json({ error: 'User mismatch' });
}
if (flowServerName && flowServerName !== serverName) {
logger.error('[MCP OAuth] Flow server mismatch', { flowId, serverName, flowServerName });
return res.status(400).json({ error: 'Invalid flow state' });
}
const pendingAge = flowState.createdAt ? Date.now() - flowState.createdAt : Infinity;
const isFreshPendingFlow = flowState.status === 'PENDING' && pendingAge < PENDING_STALE_MS;
if (!isFreshPendingFlow) {
logger.error('[MCP OAuth] Flow is not active for initiation', {
flowId,
status: flowState.status,
pendingAge,
});
return res.status(400).json({ error: 'Invalid flow state' });
}
if (typeof storedAuthorizationUrl === 'string' && storedAuthorizationUrl.length > 0) {
logger.debug('[MCP OAuth] Reusing stored authorization URL', {
serverName,
userId,
flowId,
});
setOAuthCsrfCookie(res, flowId, OAUTH_CSRF_COOKIE_PATH);
return res.redirect(storedAuthorizationUrl);
}
if (!serverUrl || !oauthConfig) {
logger.error('[MCP OAuth] Missing server URL or OAuth config in flow state');
return res.status(400).json({ error: 'Invalid flow state' });
}
const configServers = await resolveConfigServers(req);
const oauthHeaders = await getOAuthHeaders(serverName, userId, configServers);
const registry = getMCPServersRegistry();
const { allowedDomains, allowedAddresses } = await registry.resolveAllowlists({
userId,
role: req.user?.role,
});
const {
authorizationUrl,
flowId: oauthFlowId,
flowMetadata,
} = await MCPOAuthHandler.initiateOAuthFlow(
serverName,
serverUrl,
userId,
oauthHeaders,
oauthConfig,
allowedDomains,
undefined,
allowedAddresses,
getTenantId(),
);
logger.debug('[MCP OAuth] OAuth flow initiated', { oauthFlowId, authorizationUrl });
const oldState = flowState.metadata?.state;
if (typeof oldState === 'string') {
await MCPOAuthHandler.deleteStateMapping(oldState, flowManager);
}
const metadataWithUrl = { ...flowMetadata, authorizationUrl, tenantId: getTenantId() };
await flowManager.initFlow(oauthFlowId, 'mcp_oauth', metadataWithUrl);
await MCPOAuthHandler.storeStateMapping(flowMetadata.state, oauthFlowId, flowManager);
setOAuthCsrfCookie(res, oauthFlowId, OAUTH_CSRF_COOKIE_PATH);
res.redirect(authorizationUrl);
} catch (error) {
logger.error('[MCP OAuth] Failed to initiate OAuth', error);
res.status(500).json({ error: 'Failed to initiate OAuth' });
}
});
/**
* OAuth callback handler
* This handles the OAuth callback after the user has authorized the application
*/
router.get('/:serverName/oauth/callback', async (req, res) => {
const basePath = getBasePath();
try {
const { serverName } = req.params;
const { code, state, error: oauthError } = req.query;
logger.debug('[MCP OAuth] Callback received', {
serverName,
code: code ? 'present' : 'missing',
state,
error: oauthError,
});
if (oauthError) {
logger.error('[MCP OAuth] OAuth error received', { error: oauthError });
// Gate failFlow behind callback validation to prevent DoS via leaked state
if (state && typeof state === 'string') {
try {
const flowsCache = getLogStores(CacheKeys.FLOWS);
const flowManager = getFlowStateManager(flowsCache);
const flowId = await MCPOAuthHandler.resolveStateToFlowId(state, flowManager);
if (flowId) {
const parsed = MCPOAuthHandler.parseFlowId(flowId);
if (!parsed) {
logger.warn('[MCP OAuth] Invalid flow ID format for OAuth error callback', {
flowId,
});
} else {
const hasCsrf = validateOAuthCsrf(req, res, flowId, OAUTH_CSRF_COOKIE_PATH);
const hasSession = !hasCsrf && validateOAuthSession(req, parsed.userId);
if (hasCsrf || hasSession) {
/** A stale mapping can resolve a superseded attempt's state to the
* current flow (deterministic flow ids); only fail the flow this
* error callback actually belongs to */
const flowMeta = await MCPOAuthHandler.getFlowState(flowId, flowManager);
if (flowMeta?.state === state) {
await flowManager.failFlow(flowId, 'mcp_oauth', String(oauthError));
logger.debug('[MCP OAuth] Marked flow as FAILED with OAuth error', {
flowId,
error: oauthError,
});
} else {
logger.warn('[MCP OAuth] Skipping failFlow for superseded OAuth error callback', {
flowId,
});
}
}
}
}
} catch (err) {
logger.debug('[MCP OAuth] Could not mark flow as failed', err);
}
}
return res.redirect(
`${basePath}/oauth/error?error=${encodeURIComponent(String(oauthError))}`,
);
}
if (!code || typeof code !== 'string') {
logger.error('[MCP OAuth] Missing or invalid code');
return res.redirect(`${basePath}/oauth/error?error=missing_code`);
}
if (!state || typeof state !== 'string') {
logger.error('[MCP OAuth] Missing or invalid state');
return res.redirect(`${basePath}/oauth/error?error=missing_state`);
}
const flowsCache = getLogStores(CacheKeys.FLOWS);
const flowManager = getFlowStateManager(flowsCache);
const flowId = await MCPOAuthHandler.resolveStateToFlowId(state, flowManager);
if (!flowId) {
logger.error('[MCP OAuth] Could not resolve state to flow ID', { state });
return res.redirect(`${basePath}/oauth/error?error=invalid_state`);
}
logger.debug('[MCP OAuth] Resolved flow ID from state', { flowId });
const parsedFlowId = MCPOAuthHandler.parseFlowId(flowId);
if (!parsedFlowId) {
logger.error('[MCP OAuth] Invalid flow ID format', { flowId });
return res.redirect(`${basePath}/oauth/error?error=invalid_state`);
}
const hasCsrf = validateOAuthCsrf(req, res, flowId, OAUTH_CSRF_COOKIE_PATH);
const hasSession = !hasCsrf && validateOAuthSession(req, parsedFlowId.userId);
let hasActiveFlow = false;
if (!hasCsrf && !hasSession) {
const pendingFlow = await flowManager.getFlowState(flowId, 'mcp_oauth');
const pendingAge = pendingFlow?.createdAt ? Date.now() - pendingFlow.createdAt : Infinity;
hasActiveFlow = pendingFlow?.status === 'PENDING' && pendingAge < PENDING_STALE_MS;
if (hasActiveFlow) {
logger.debug(
'[MCP OAuth] CSRF/session cookies absent, validating via active PENDING flow',
{
flowId,
},
);
}
}
if (!hasCsrf && !hasSession && !hasActiveFlow) {
logger.error(
'[MCP OAuth] CSRF validation failed: no valid CSRF cookie, session cookie, or active flow',
{
flowId,
hasCsrfCookie: !!req.cookies?.[OAUTH_CSRF_COOKIE],
hasSessionCookie: !!req.cookies?.[OAUTH_SESSION_COOKIE],
},
);
return res.redirect(`${basePath}/oauth/error?error=csrf_validation_failed`);
}
logger.debug('[MCP OAuth] Getting flow state for flowId: ' + flowId);
const flowState = await MCPOAuthHandler.getFlowState(flowId, flowManager);
if (!flowState) {
logger.error('[MCP OAuth] Flow state not found for flowId:', flowId);
return res.redirect(`${basePath}/oauth/error?error=invalid_state`);
}
/**
* Flow ids are deterministic (userId:serverName), so a stale state mapping
* can resolve to a newer flow for the same server. The stored state is the
* only per-attempt nonce; a mismatch means this callback belongs to a
* superseded authorization attempt and must not consume the current flow.
*/
if (flowState.state !== state) {
logger.error('[MCP OAuth] State mismatch for flow', { flowId, serverName });
return res.redirect(`${basePath}/oauth/error?error=invalid_state`);
}
logger.debug('[MCP OAuth] Flow state details', {
serverName: flowState.serverName,
userId: flowState.userId,
hasMetadata: !!flowState.metadata,
hasClientInfo: !!flowState.clientInfo,
hasCodeVerifier: !!flowState.codeVerifier,
});
/** Check if this flow has already been completed (idempotency protection) */
const currentFlowState = await flowManager.getFlowState(flowId, 'mcp_oauth');
if (currentFlowState?.status === 'COMPLETED') {
logger.warn('[MCP OAuth] Flow already completed, preventing duplicate token exchange', {
flowId,
serverName,
});
return res.redirect(`${basePath}/oauth/success?serverName=${encodeURIComponent(serverName)}`);
}
const isStalePendingFlow =
currentFlowState?.status === 'PENDING' &&
(!currentFlowState.createdAt || Date.now() - currentFlowState.createdAt >= PENDING_STALE_MS);
if (currentFlowState?.status === 'FAILED' || isStalePendingFlow) {
logger.warn('[MCP OAuth] Refusing token exchange for terminal flow', {
flowId,
serverName,
status: currentFlowState.status,
});
return res.redirect(`${basePath}/oauth/error?error=invalid_state`);
}
logger.debug('[MCP OAuth] Completing OAuth flow');
/**
* Restore tenant context for the callback body. The callback is a cross-origin
* redirect from the OAuth provider, so SameSite=Strict cookies (including the
* JWT) are not sent. The tenantId was stored in the flow metadata at initiation
* time when the user was authenticated.
*/
const runWithTenant = async (fn) => {
const flowTenantId = flowState.tenantId;
if (flowTenantId && !getTenantId()) {
return tenantStorage.run({ tenantId: flowTenantId }, fn);
}
return fn();
};
await runWithTenant(async () => {
const oauthHeaders =
flowState.oauthHeaders ?? (await getOAuthHeaders(serverName, flowState.userId));
const tokens = await MCPOAuthHandler.completeOAuthFlow(
flowId,
code,
flowManager,
oauthHeaders,
async (exchangedTokens) => {
if (!flowState?.userId) {
return exchangedTokens;
}
let storedTokens;
try {
storedTokens =
(await MCPTokenStorage.storeTokens({
userId: flowState.userId,
serverName,
tokens: exchangedTokens,
createToken: db.createToken,
updateToken: db.updateToken,
deleteTokens: db.deleteTokens,
findToken: db.findToken,
clientInfo: flowState.clientInfo,
metadata: MCPOAuthHandler.buildStoredClientMetadata(
flowState.metadata,
flowState.resourceMetadata,
flowState.serverUrl,
flowState.clientSource,
),
})) ?? exchangedTokens;
logger.debug('[MCP OAuth] Stored OAuth tokens before completing callback flow', {
serverName,
userId: flowState.userId,
});
} catch (error) {
logger.error('[MCP OAuth] Failed to store OAuth tokens before flow completion', error);
throw error;
}
/**
* Clear any cached `mcp_get_tokens` flow result before the OAuth flow wakes its
* waiters, so they cannot observe stale credentials after completion.
*/
if (typeof flowManager?.deleteFlow === 'function') {
try {
const tokenFlowId = MCPOAuthHandler.generateTokenFlowId(
flowState.userId,
serverName,
flowState.tenantId,
);
await clearGetTokensFlow({
flowManager,
flowId: tokenFlowId,
tokens: storedTokens,
});
if (tokenFlowId !== flowId) {
await clearGetTokensFlow({
flowManager,
flowId,
tokens: storedTokens,
});
}
} catch (error) {
logger.warn('[MCP OAuth] Failed to clear cached token flow state', error);
}
}
return storedTokens;
},
);
logger.info('[MCP OAuth] OAuth flow completed, tokens received in callback route');
try {
if (flowState.userId !== 'system') {
const user = { id: flowState.userId };
/** Merged config (incl. Config-tier overlays) so the reconnection and
* the cache gate both see request-scoped servers the base registry
* lookup misses */
let serverConfig;
try {
const allConfigs = await resolveAllMcpConfigs(flowState.userId);
serverConfig = allConfigs?.[serverName];
} catch (error) {
logger.warn(
`[MCP OAuth] Could not resolve server config for ${serverName} before reconnecting:`,
error,
);
}
const requestScoped = serverConfig
? requiresEphemeralUserConnection(serverConfig)
: false;
if (requestScoped) {
logger.info(
`[MCP OAuth] Deferring post-OAuth connection for request-scoped server ${serverName} until its first chat use`,
);
getOAuthReconnectionManager().clearReconnection(flowState.userId, serverName);
} else {
const mcpManager = getMCPManager(flowState.userId);
logger.debug(`[MCP OAuth] Attempting to reconnect ${serverName} with new OAuth tokens`);
/**
* Without this, getUserConnection resolves `headers`/`oauth_headers`
* customUserVars templates (e.g. `{{MY_VAR}}`) with no substitution
* data, so the literal placeholder is sent on this first post-callback
* connection attempt even though the user's value is already saved -
* surfaces upstream as a generic auth rejection from the MCP server.
* The other reconnect path (oauth/reinitialize route below) already
* resolves this the same way; this one was missing it.
*/
let userMCPAuthMap;
if (serverConfig?.customUserVars && typeof serverConfig.customUserVars === 'object') {
try {
userMCPAuthMap = await getUserMCPAuthMap({
userId: flowState.userId,
servers: [serverName],
findPluginAuthsByKeys: db.findPluginAuthsByKeys,
});
} catch (error) {
logger.warn(
`[MCP OAuth] Could not resolve customUserVars for ${serverName} before reconnecting:`,
error,
);
}
}
const customUserVars = getServerCustomUserVars(userMCPAuthMap, serverName);
const { snapshot, publicationGeneration } = await mcpManager.withUserConnectionLease(
{
user,
serverName,
flowManager,
serverConfig,
customUserVars,
tokenMethods: {
findToken: db.findToken,
updateToken: db.updateToken,
createToken: db.createToken,
deleteTokens: db.deleteTokens,
},
},
async (userConnection) => {
logger.info(
`[MCP OAuth] Successfully reconnected ${serverName} for user ${flowState.userId}`,
);
const oauthReconnectionManager = getOAuthReconnectionManager();
oauthReconnectionManager.clearReconnection(flowState.userId, serverName);
const snapshot =
typeof userConnection.fetchOrderedToolsSnapshot === 'function'
? await userConnection.fetchOrderedToolsSnapshot()
: await userConnection.fetchToolsSnapshot();
return {
snapshot,
publicationGeneration: mcpManager.getToolPublicationGeneration?.(userConnection),
};
},
);
if (snapshot.complete) {
await updateMCPServerTools({
userId: flowState.userId,
serverName,
tools: snapshot.tools,
serverConfig,
publicationGeneration,
});
} else {
logger.warn(
`[MCP OAuth] Preserving cached tools for ${serverName} because tools/list returned an incomplete snapshot`,
);
}
}
} else {
logger.debug(`[MCP OAuth] System-level OAuth completed for ${serverName}`);
}
} catch (error) {
logger.warn(
`[MCP OAuth] Failed to reconnect ${serverName} after OAuth, but tokens are saved:`,
error,
);
}
/** ID of the flow that the tool/connection is waiting for */
const toolFlowId = flowState.metadata?.toolFlowId;
if (toolFlowId) {
logger.debug('[MCP OAuth] Completing tool flow', { toolFlowId });
const completed = await flowManager.completeFlow(toolFlowId, 'mcp_oauth', tokens);
if (!completed) {
logger.warn(
'[MCP OAuth] Tool flow state not found during completion — waiter will time out',
{ toolFlowId },
);
}
}
}); /* end runWithTenant */
/** Redirect to success page with flowId and serverName */
const redirectUrl = `${basePath}/oauth/success?serverName=${encodeURIComponent(serverName)}`;
res.redirect(redirectUrl);
} catch (error) {
logger.error('[MCP OAuth] OAuth callback error', error);
res.redirect(`${basePath}/oauth/error?error=callback_failed`);
}
});
/**
* Get OAuth tokens for a completed flow
* This is primarily for user-level OAuth flows
*/
router.get('/oauth/tokens/:flowId', requireJwtAuth, async (req, res) => {
try {
const { flowId } = req.params;
const user = req.user;
if (!user?.id) {
return res.status(401).json({ error: 'User not authenticated' });
}
if (!canAccessOAuthFlow(flowId, user.id)) {
return res.status(403).json({ error: 'Access denied' });
}
const flowsCache = getLogStores(CacheKeys.FLOWS);
const flowManager = getFlowStateManager(flowsCache);
const flowState = await flowManager.getFlowState(flowId, 'mcp_oauth');
if (!flowState) {
return res.status(404).json({ error: 'Flow not found' });
}
if (flowState.status !== 'COMPLETED') {
return res.status(400).json({ error: 'Flow not completed' });
}
res.json({ tokens: flowState.result });
} catch (error) {
logger.error('[MCP OAuth] Failed to get tokens', error);
res.status(500).json({ error: 'Failed to get tokens' });
}
});
/**
* Set CSRF binding cookie for OAuth flows initiated outside of HTTP request/response
* (e.g. during chat via SSE). The frontend should call this before opening the OAuth URL
* so the callback can verify the browser matches the flow initiator.
*/
router.post('/:serverName/oauth/bind', requireJwtAuth, setOAuthSession, async (req, res) => {
try {
const { serverName } = req.params;
const user = req.user;
if (!user?.id) {
return res.status(401).json({ error: 'User not authenticated' });
}
const flowId = getOAuthFlowId(user.id, serverName);
setOAuthCsrfCookie(res, flowId, OAUTH_CSRF_COOKIE_PATH);
res.json({ success: true });
} catch (error) {
logger.error('[MCP OAuth] Failed to set CSRF binding cookie', error);
res.status(500).json({ error: 'Failed to bind OAuth flow' });
}
});
/**
* Check OAuth flow status
* This endpoint can be used to poll the status of an OAuth flow
*/
router.get('/oauth/status/:flowId', requireJwtAuth, async (req, res) => {
try {
const { flowId } = req.params;
const user = req.user;
if (!user?.id) {
return res.status(401).json({ error: 'User not authenticated' });
}
if (!canAccessOAuthFlow(flowId, user.id)) {
return res.status(403).json({ error: 'Access denied' });
}
const flowsCache = getLogStores(CacheKeys.FLOWS);
const flowManager = getFlowStateManager(flowsCache);
const flowState = await flowManager.getFlowState(flowId, 'mcp_oauth');
if (!flowState) {
return res.status(404).json({ error: 'Flow not found' });
}
res.json({
status: flowState.status,
completed: flowState.status === 'COMPLETED',
failed: flowState.status === 'FAILED',
error: flowState.error,
});
} catch (error) {
logger.error('[MCP OAuth] Failed to get flow status', error);
res.status(500).json({ error: 'Failed to get flow status' });
}
});
/**
* Cancel OAuth flow
* This endpoint cancels a pending OAuth flow
*/
router.post('/oauth/cancel/:serverName', requireJwtAuth, async (req, res) => {
try {
const { serverName } = req.params;
const user = req.user;
if (!user?.id) {
return res.status(401).json({ error: 'User not authenticated' });
}
logger.info(`[MCP OAuth Cancel] Cancelling OAuth flow for ${serverName} by user ${user.id}`);
const flowsCache = getLogStores(CacheKeys.FLOWS);
const flowManager = getFlowStateManager(flowsCache);
const flowId = getOAuthFlowId(user.id, serverName);
const flowState = await flowManager.getFlowState(flowId, 'mcp_oauth');
if (!flowState) {
logger.debug(`[MCP OAuth Cancel] No active flow found for ${serverName}`);
return res.json({
success: true,
message: 'No active OAuth flow to cancel',
});
}
await flowManager.failFlow(flowId, 'mcp_oauth', 'User cancelled OAuth flow');
logger.info(`[MCP OAuth Cancel] Successfully cancelled OAuth flow for ${serverName}`);
res.json({
success: true,
message: `OAuth flow for ${serverName} cancelled successfully`,
});
} catch (error) {
logger.error('[MCP OAuth Cancel] Failed to cancel OAuth flow', error);
res.status(500).json({ error: 'Failed to cancel OAuth flow' });
}
});
function createMCPStatusRuntimeContext(user, mcpConfig, serverNames) {
const customUserVarServers = serverNames.filter((serverName) => {
const customUserVars = mcpConfig[serverName]?.customUserVars;
return (
customUserVars && typeof customUserVars === 'object' && Object.keys(customUserVars).length > 0
);
});
let userMCPAuthMapPromise;
let mcpAllowlistsPromise;
const loadUserMCPAuthMap = () => {
if (!customUserVarServers.length) {
return Promise.resolve(undefined);
}
userMCPAuthMapPromise ??= getUserMCPAuthMap({
userId: user.id,
servers: customUserVarServers,
findPluginAuthsByKeys: db.findPluginAuthsByKeys,
});
return userMCPAuthMapPromise;
};
const loadMCPAllowlists = () => {
mcpAllowlistsPromise ??= getMCPServersRegistry().resolveAllowlists({
userId: user.id,
role: user.role,
});
return mcpAllowlistsPromise;
};
return { user: createSafeUser(user), loadUserMCPAuthMap, loadMCPAllowlists };
}
function getMCPReinitializeOAuthTimeout(oauthExpiresAt) {
if (typeof oauthExpiresAt !== 'number' || !Number.isFinite(oauthExpiresAt)) {
return mcpSettings.OAUTH_HANDLING_TIMEOUT;
}
return Math.max(0, oauthExpiresAt - Date.now());
}
/**
* Reinitialize MCP server
* This endpoint allows reinitializing a specific MCP server
*/
router.post(
'/:serverName/reinitialize',
requireJwtAuth,
checkMCPUsePermissions,
setOAuthSession,
async (req, res) => {
try {
const { serverName } = req.params;
const user = createSafeUser(req.user);
if (!user.id) {
return res.status(401).json({ error: 'User not authenticated' });
}
logger.info(`[MCP Reinitialize] Reinitializing server: ${serverName}`);
const mcpManager = getMCPManager();
const configServers = await resolveConfigServers(req);
const serverConfig = await getMCPServersRegistry().getServerConfig(
serverName,
user.id,
configServers,
);
if (!serverConfig) {
return res.status(404).json({
error: `MCP server '${serverName}' not found in configuration`,
});
}
try {
await invalidateCachedTools({ userId: user.id, serverName });
} finally {
await mcpManager.disconnectUserConnection(user.id, serverName);
}
logger.info(
`[MCP Reinitialize] Disconnected existing user connection for server: ${serverName}`,
);
/** @type {Record<string, Record<string, string>> | undefined} */
let userMCPAuthMap;
if (serverConfig.customUserVars && typeof serverConfig.customUserVars === 'object') {
userMCPAuthMap = await getUserMCPAuthMap({
userId: user.id,
servers: [serverName],
findPluginAuthsByKeys: db.findPluginAuthsByKeys,
});
}
const oboIdentityContext = createAuthIdentityContext({
user: req.user,
tenantId: getTenantId(),
});
const result = await reinitMCPServer({
user,
serverName,
serverConfig,
configServers,
userMCPAuthMap,
upstreamTokenProvider: createOpenIDSessionTokenProvider({
req,
res,
user: req.user,
identityContext: oboIdentityContext,
tokenPreference: 'access_token',
}),
oboIdentityContext,
});
if (!result) {
return res.status(500).json({ error: 'Failed to reinitialize MCP server for user' });
}
const {
success,
message,
oauthRequired,
oauthUrl,
oauthExpiresAt,
failureReason,
missingUserVars,
connectionDeferred,
} = result;
let flowId;
if (oauthRequired) {
flowId = getOAuthFlowId(user.id, serverName);
setOAuthCsrfCookie(res, flowId, OAUTH_CSRF_COOKIE_PATH);
}
res.json({
success,
message,
oauthUrl,
flowId,
oauthTimeout: oauthRequired ? getMCPReinitializeOAuthTimeout(oauthExpiresAt) : undefined,
serverName,
oauthRequired,
failureReason,
missingUserVars,
connectionDeferred,
});
} catch (error) {
logger.error('[MCP Reinitialize] Unexpected error', error);
res.status(500).json({ error: 'Internal server error' });
}
},
);
/**
* Get connection status for all MCP servers
* This endpoint returns all app level and user-scoped connection statuses from MCPManager without disconnecting idle connections
*/
router.get('/connection/status', requireJwtAuth, async (req, res) => {
try {
const user = req.user;
if (!user?.id) {
return res.status(401).json({ error: 'User not authenticated' });
}
const { mcpConfig, appConnections, userConnections, oauthServers } = await getMCPSetupData(
user.id,
{ role: user.role, tenantId: getTenantId() },
);
const runtimeContext = createMCPStatusRuntimeContext(user, mcpConfig, Object.keys(mcpConfig));
const connectionStatus = Object.fromEntries(
await Promise.all(
Object.entries(mcpConfig).map(async ([serverName, config]) => {
try {
const status = await getServerConnectionStatus(
user.id,
serverName,
config,
appConnections,
userConnections,
oauthServers,
runtimeContext,
);
return [serverName, status];
} catch (error) {
const message = `Failed to get status for server "${serverName}"`;
logger.error(`[MCP Connection Status] ${message},`, error);
return [
serverName,
{
connectionState: 'error',
requiresOAuth: oauthServers.has(serverName),
...(requiresEphemeralUserConnection(config) && { requestScoped: true }),
...(requiresEphemeralUserConnection(config) &&
hasCustomUserVars(config) && { configurationState: 'needs_configuration' }),
authorizationState: oauthServers.has(serverName) ? 'error' : 'not_required',
error: message,
},
];
}
}),
),
);
res.json({
success: true,
connectionStatus,
oauthTimeout: mcpSettings.OAUTH_HANDLING_TIMEOUT,
});
} catch (error) {
logger.error('[MCP Connection Status] Failed to get connection status', error);
res.status(500).json({ error: 'Failed to get connection status' });
}
});
/**
* Get connection status for a single MCP server
* This endpoint returns the connection status for a specific server for a given user
*/
router.get('/connection/status/:serverName', requireJwtAuth, async (req, res) => {
try {
const user = req.user;
const { serverName } = req.params;
if (!user?.id) {
return res.status(401).json({ error: 'User not authenticated' });
}
const { mcpConfig, appConnections, userConnections, oauthServers } = await getMCPSetupData(
user.id,
{ role: user.role, tenantId: getTenantId() },
);
if (!mcpConfig[serverName]) {
return res
.status(404)
.json({ error: `MCP server '${serverName}' not found in configuration` });
}
const runtimeContext = createMCPStatusRuntimeContext(user, mcpConfig, [serverName]);
const serverStatus = await getServerConnectionStatus(
user.id,
serverName,
mcpConfig[serverName],
appConnections,
userConnections,
oauthServers,
runtimeContext,
);
res.json({
success: true,
serverName,
connectionStatus: serverStatus.connectionState,
requiresOAuth: serverStatus.requiresOAuth,
requestScoped: serverStatus.requestScoped,
configurationState: serverStatus.configurationState,
authorizationState: serverStatus.authorizationState,
});
} catch (error) {
logger.error(
`[MCP Per-Server Status] Failed to get connection status for ${req.params.serverName}`,
error,
);
res.status(500).json({ error: 'Failed to get connection status' });
}
});
/**
* Check which authentication values exist for a specific MCP server
* This endpoint returns only boolean flags indicating if values are set, not the actual values
*/
router.get('/:serverName/auth-values', requireJwtAuth, checkMCPUsePermissions, async (req, res) => {
try {
const { serverName } = req.params;
const user = req.user;
if (!user?.id) {
return res.status(401).json({ error: 'User not authenticated' });
}
const configServers = await resolveConfigServers(req);
const serverConfig = await getMCPServersRegistry().getServerConfig(
serverName,
user.id,
configServers,
);
if (!serverConfig) {
return res.status(404).json({
error: `MCP server '${serverName}' not found in configuration`,
});
}
const pluginKey = `${Constants.mcp_prefix}${serverName}`;
const authValueFlags = {};
if (serverConfig.customUserVars && typeof serverConfig.customUserVars === 'object') {
for (const varName of Object.keys(serverConfig.customUserVars)) {
try {
const value = await getUserPluginAuthValue(user.id, varName, false, pluginKey);
authValueFlags[varName] = !!(value && value.length > 0);
} catch (err) {
logger.error(
`[MCP Auth Value Flags] Error checking ${varName} for user ${user.id}:`,
err,
);
authValueFlags[varName] = false;
}
}
}
res.json({
success: true,
serverName,
authValueFlags,
});
} catch (error) {
logger.error(
`[MCP Auth Value Flags] Failed to check auth value flags for ${req.params.serverName}`,
error,
);
res.status(500).json({ error: 'Failed to check auth value flags' });
}
});
async function getOAuthHeaders(serverName, userId, configServers) {
const serverConfig = await getMCPServersRegistry().getServerConfig(
serverName,
userId,
configServers,
);
return serverConfig?.oauth_headers ?? {};
}
/**
MCP Server CRUD Routes (User-Managed MCP Servers)
*/
/**
* Get list of accessible MCP servers
* @route GET /api/mcp/servers
* @param {Object} req.query - Query parameters for pagination and search
* @param {number} [req.query.limit] - Number of results per page
* @param {string} [req.query.after] - Pagination cursor
* @param {string} [req.query.search] - Search query for title/description
* @returns {MCPServerListResponse} 200 - Success response - application/json
*/
router.get('/servers', requireJwtAuth, checkMCPUsePermissions, getMCPServersList);
/**
* Create a new MCP server
* @route POST /api/mcp/servers
* @param {MCPServerCreateParams} req.body - The MCP server creation parameters.
* @returns {MCPServer} 201 - Success response - application/json
*/
router.post('/servers', requireJwtAuth, checkMCPCreate, createMCPServerController);
/**
* Get single MCP server by ID
* @route GET /api/mcp/servers/:serverName
* @param {string} req.params.serverName - MCP server identifier.
* @returns {MCPServer} 200 - Success response - application/json
*/
router.get(
'/servers/:serverName',
requireJwtAuth,
checkMCPUsePermissions,
canAccessMCPServerResource({
requiredPermission: PermissionBits.VIEW,
resourceIdParam: 'serverName',
}),
getMCPServerById,
);
/**
* Update MCP server
* @route PATCH /api/mcp/servers/:serverName
* @param {string} req.params.serverName - MCP server identifier.
* @param {MCPServerUpdateParams} req.body - The MCP server update parameters.
* @returns {MCPServer} 200 - Success response - application/json
*/
router.patch(
'/servers/:serverName',
requireJwtAuth,
checkMCPCreate,
canAccessMCPServerResource({
requiredPermission: PermissionBits.EDIT,
resourceIdParam: 'serverName',
}),
updateMCPServerController,
);
/**
* Delete MCP server
* @route DELETE /api/mcp/servers/:serverName
* @param {string} req.params.serverName - MCP server identifier.
* @returns {Object} 200 - Success response - application/json
*/
router.delete(
'/servers/:serverName',
requireJwtAuth,
checkMCPCreate,
canAccessMCPServerResource({
requiredPermission: PermissionBits.DELETE,
resourceIdParam: 'serverName',
}),
deleteMCPServerController,
);
module.exports = router;