Drop form-action from the default Content Security Policy on the OAuth
consent page. Chrome enforces form-action across the entire redirect
chain, which breaks flows where an HTTPS callback internally redirects
to a custom scheme (e.g. claude://, cursor://). Since the form posts
to itself and all redirects are server-controlled, form-action adds
no security value here.
Also forward the consent_csp_policy parameter through all concrete
OAuth providers (Auth0, Azure, Google, GitHub, Discord, WorkOS, AWS
Cognito, OCI) so users can override the CSP without accessing private
attributes.
* Replace vendored DI with uncalled-for
FastMCP vendored a minimal DI engine extracted from Docket (~164 lines)
with try/except fallback patterns everywhere. The `uncalled-for` package
is a clean, typed extraction of this same system, and since Docket will
also depend on it (chrisguidry/docket#353), `uncalled_for.Dependency`
becomes the single canonical base class.
This deletes the `_vendor/docket_di/` directory, replaces all the
try/except import patterns with direct `uncalled_for` imports, and
updates the `Dependency.execution` → `current_execution` ContextVar
references to match the Docket branch. The `Progress` class now
delegates to an internal impl and returns `self` from `__aenter__`
(matching Docket's pattern) so that ty's generic resolution works
without `type: ignore` suppressions.
Temporarily points pydocket at the `use-uncalled-for` branch so both
sides can be validated together in CI.
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Re-export Dependency from fastmcp.dependencies
Internal code like azure.py should import from the fastmcp namespace
rather than reaching into uncalled_for directly.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Import Dependency from fastmcp namespace in tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add generic type parameters to Dependency subclasses
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Mention uncalled-for in DI docs
The DI engine now comes from uncalled-for, so the docs should credit
it alongside Docket. Also updates the Docket docs link to docket.lol.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Point docket dependency at main
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Bump uncalled-for pin to >=0.2.0
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Fix uncalled-for imports for 0.2.0 API changes
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Support Shared() dependencies without docket
Enters a SharedContext at server lifetime so that Shared() dependencies
from uncalled-for resolve once and are cached across tool/resource/prompt
calls. When running with docket, the Worker already handles this; this
covers the non-docket path and direct call_tool() usage.
Also re-exports Shared from fastmcp.dependencies.
Closes#3251
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Bump docket lockfile to latest main
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Remove duplicate test classes from rebase conflict resolution
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Point docket dependency at pydocket>=0.18.0 release
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Pair SharedContext __aenter__ with __aexit__ in Context lifecycle
The old `_ensure_shared_context` on the server called `__aenter__()` on a
lazy `SharedContext` but never `__aexit__()`, leaking the exit stack and
its resources. Moved the SharedContext management into Context's own
enter/exit so it's properly paired: when docket is available the lifespan
handles it, otherwise Context creates and cleans up a per-request one.
Updated Shared() tests to use Client (which runs the lifespan) rather
than calling server methods directly, since cross-request sharing
requires a lifespan.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Hoist SharedContext import to module level
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Adds the PropelAuthProvider which delegates to the IntrospectionTokenVerifier
and optionally does an additional resource check.
Adds an example server and client which makes an authenticated request
and gets information from the token.
Updates the documentation (but only for v3 as this isn't in v2).
Increase performance test threshold from 100ms to 1.0s. Windows CI runners
are slower than Linux, and the 100ms threshold was too tight. The test's
intent is to catch obvious regressions (e.g., accidentally re-introducing
code generation), not to precisely benchmark.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add MultiAuth for composing multiple token verification sources
🤖 Generated with Claude Code
https://claude.ai/code/session_01WwKYDCqjM2FqYwY5ZNVvjb
* Fix ruff lint/format in MultiAuth tests
🤖 Generated with Claude Code
https://claude.ai/code/session_01WwKYDCqjM2FqYwY5ZNVvjb
* Fix MultiAuth well-known route delegation and empty scopes handling
🤖 Generated with Claude Code
https://claude.ai/code/session_01WwKYDCqjM2FqYwY5ZNVvjb
* Harden MultiAuth: exception resilience, mcp_path propagation, test coverage
- verify_token now catches exceptions from individual sources and
continues to the next, so one broken verifier can't take down the
whole chain
- set_mcp_path propagates to verifiers, not just the server
- Fix jwks_url→jwks_uri typo in class docstring
- Add tests for raising verifiers, valid-token HTTP acceptance,
and set_mcp_path propagation
* Clean up MultiAuth: precompute sources, deduplicate test helpers
* Fix version badges to 3.1.0
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: Add search transforms for tool discovery
RegexSearchTransform and BM25SearchTransform collapse large tool
catalogs into a search interface so LLMs discover tools on demand
instead of receiving the full listing.
* chore: Update SDK documentation
* fix: call_tool recursion guard, atomic BM25 rebuild, hash includes descriptions
* Extract CatalogTransform base class for catalog-aware transforms
Transforms that replace list_tools() with synthetic components (like
search) need to read the real catalog at call time without triggering
their own replacement logic. CatalogTransform handles the re-entrant
bypass via per-instance ContextVar, exposing transform_tools() as the
subclass hook and get_tool_catalog() for catalog access.
* Add search transform examples for regex and BM25
* Add README for search transform examples
* Polish search example clients with rich output
* Remove hardcoded tool counts from search example subtitles
* Clarify that review bot feedback should be evaluated on its merits
* Expand search transform docs with proper hierarchy
---------
Co-authored-by: marvin-context-protocol[bot] <225465937+marvin-context-protocol[bot]@users.noreply.github.com>
* Fix ty 0.0.19 type errors
🤖 Generated with Claude Code
* Fix ruff formatting in sampling/run.py
🤖 Generated with Claude Code
https://claude.ai/code/session_01GWzbyF1vHvVeS4yJ5bhScf
---------
Co-authored-by: Claude <noreply@anthropic.com>
* Fix background Context request correlation
* Make OptionalCurrentContext type-safe
Refactor OptionalCurrentContext to wrap CurrentContext instead of overriding __aenter__ with a wider return type. Adds a background-task origin_request_id round-trip test and applies ruff formatting.
* Fix ty ignore syntax in OpenAPI provider
* Fix flaky rate limiting and ping timing tests
* Assert rate limit error message in flaky test fix
* Catch only ToolError in rate limiting test
* Fix non-serializable state lost between middleware and tools
Inherit _request_state dict from parent Context in __aenter__ so
middleware and tool contexts share the same in-memory state.
Closes#3228
* chore: Update SDK documentation
---------
Co-authored-by: marvin-context-protocol[bot] <225465937+marvin-context-protocol[bot]@users.noreply.github.com>
* Update repository references from jlowin/fastmcp to prefecthq/fastmcp
* Retrigger CI after repo transfer
* chore: Update SDK documentation
* Only run deep triage on bug issues for jlowin
---------
Co-authored-by: marvin-context-protocol[bot] <225465937+marvin-context-protocol[bot]@users.noreply.github.com>
* Add consent binding cookie to prevent confused deputy attacks (GHSA-rww4-4w9c-7733)
The OAuthProxy's consent page verified user intent but didn't bind the
consenting browser to the IdP callback. An attacker could intercept the
upstream authorization URL after consent and send it to a victim, whose
browser would complete the flow without having the consent cookie.
This adds a signed consent binding cookie set during consent approval
(both manual and auto-approve paths) and verified in the IdP callback
handler. A different browser won't have this cookie and gets a 403.
* Use startswith for URL assertion in consent binding test
* Store consent bindings as per-transaction map to support parallel flows
* Only accept __Host- consent binding cookie on HTTPS
* chore: Update SDK documentation
---------
Co-authored-by: marvin-context-protocol[bot] <225465937+marvin-context-protocol[bot]@users.noreply.github.com>
* fix: restore request context in StatefulProxyClient handlers
StatefulProxyClient reuses sessions across requests, so its receive-loop
task inherits a stale request_ctx ContextVar from the first request.
Server-initiated messages (elicitation, sampling, etc.) that depend on
related_request_id routing get sent to a closed stream and hang forever.
Closes#3169
* chore: Update SDK documentation
---------
Co-authored-by: marvin-context-protocol[bot] <225465937+marvin-context-protocol[bot]@users.noreply.github.com>
* fix: guard client pagination loops against misbehaving servers
Treat empty/falsy nextCursor as end-of-pagination and detect cursor
cycles across all client list methods and the server context proxy
helper.
* chore: Update SDK documentation
---------
Co-authored-by: marvin-context-protocol[bot] <225465937+marvin-context-protocol[bot]@users.noreply.github.com>
Moves relay_elicitation() into elicitation.py so it can reuse
handle_task_input() for the Redis push instead of duplicating that logic.
notifications.py just detects the trigger and calls it.
Also fixes the related-task metadata key from modelcontextprotocol.io/ to
io.modelcontextprotocol/ to match the current spec:
https://modelcontextprotocol.io/specification/2025-11-25/basic/utilities/tasks
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When a background task calls ctx.elicit(), the notification subscriber now
detects the input_required notification and sends a standard elicitation/create
request to the client via session.elicit(). The client's elicitation_handler
fires, and the relay pushes the response to Redis for the blocked worker.
This means clients can respond to background task elicitation using the same
elicitation_handler they'd use for any other elicitation — no need to interact
with Redis or call handle_task_input() directly.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
