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.
* Add tests for two-stage pattern, empty full-detail results, empty inputs
* Add ListTools, search limit, catalog size annotation; split tests
Co-authored-by: Claude <noreply@anthropic.com>
* Remove BM25 internal cap so Search.limit is the sole truncation point
* Pass default_limit to BM25 instead of arbitrary high cap
---------
Co-authored-by: Claude <noreply@anthropic.com>
* Add Google GenAI sampling handler
Co-authored-by: Bill Easton <strawgate@users.noreply.github.com>
* chore: Update SDK documentation
* Filter non-Gemini model hints in _get_model
Match the Anthropic/OpenAI handler pattern of only selecting
provider-compatible models from hints.
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Bill Easton <strawgate@users.noreply.github.com>
Co-authored-by: marvin-context-protocol[bot] <225465937+marvin-context-protocol[bot]@users.noreply.github.com>
Co-authored-by: Jeremiah Lowin <153965+jlowin@users.noreply.github.com>
* feat: auto-sync MCPMixin decorators with from_function signatures
Replace hard-coded parameter lists in mcp_tool/mcp_resource/mcp_prompt
with **kwargs validated at decoration time against inspect.signature of
the underlying from_function. Registration methods now splat **kwargs
through directly, so any new from_function parameter is supported
automatically without touching the contrib module.
Also fixes enabled=False being silently ignored during registration.
🤖 Generated with Claude Code
* fix: make enabled keyword-only in mcp_tool and mcp_prompt
Prevents silent positional arg remapping — callers who previously
passed description/title as the second positional arg would have
silently bound to enabled instead.
🤖 Generated with Claude Code
* connect ProxyClient via AsyncExitStack
* test session persistence for multiple tool calls
* switch to StatefulProxyClient
* changed to StatefulProxyClient
* stash weakref instead of context
* clear transport list before building new session
* Decompose CodeMode into composable discovery tools
CodeMode now owns only the execute sandbox. Discovery tools (search,
get_schema, etc.) are composable via the discovery_tools parameter.
Each is a Callable[[GetToolCatalog], Tool] factory.
Ships SearchTool (lightweight name+description results) and SchemaTool
(brief markdown or full JSON schemas by tool name) as built-in defaults.
* Rename to Search/GetSchemas/Tags, add tag filtering, fix bugs
- Rename SearchTool→Search, SchemaTool→GetSchemas, Categories→Tags
- Add tags parameter to Search for LLM-side tag filtering
- Add Tags discovery tool for browsing tools by tag
- Fix shared singleton default factories (now per-instance)
- Fix get_schema full mode returning invalid JSON on partial matches
- Fix "untagged" filter inconsistency between Tags and Search
- Split serialization tests to comply with loq line limit
- Rewrite docs for conceptual clarity
* Add three-tier detail levels, remove default_arguments, rename Tags→GetTags, rewrite docs
* Clean up __all__ exports, return valid JSON for empty full-detail results
* 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).
The client timeout of 0.1s was too tight — the SSE handshake alone
consumed it under CI load before the tool call ever started. Raised
to 0.5s which still validates the precedence logic.
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>
* Add prefab auto-wiring for MCP Apps (#3119)
Tools that return prefab types (UIResponse, Component) automatically get
wired to the shared prefab renderer resource. Works via app=True,
return type inference, or both.
* Prefab compatibility updates
* Use published prefab-ui >=0.6.0, remove local source override
* Migrate UIResponse to PrefabApp for Prefab UI integration
PrefabApp is a pure data object with to_json(), html(), and csp()
methods. Tools can return PrefabApp, bare Components, or
ToolResult with structured_content for custom LLM fallback text.
* Add Prefab UI apps documentation
* Add mini apps and full apps documentation pages
Mini apps covers the common single-screen patterns: charts (bar, line,
area, pie), data tables with sorting/search/pagination, forms (manual
and Pydantic-generated), status displays, conditional content, and
layout composition with tabs and accordions.
Full apps covers multi-page applications using Pages/Page components,
shared state across pages, and using ToolCall with result_key for
server-driven state updates.
* Reframe apps docs around motivation, add generative UIs page
The docs now lead with the problem — MCP tools stuff data into the LLM
context window, and building HTML/JS/CSS frontends is a non-starter for
Python developers — before introducing Prefab as the solution. Mini apps
are framed as the primary use case: focused, single-purpose UIs that
present data visually and collect structured input.
New generative UIs page covers the concept of LLMs producing component
JSON directly, enabling adaptive dashboards, tailored forms, and
exploratory workflows.
* Tag Prefab docs pages as SOON instead of NEW
* Rename Low-Level API to Custom HTML Apps
The page is about using the MCP Apps extension directly, not a FastMCP
or Prefab internal API. Reframed to make clear this is the open MCP
protocol with FastMCP providing convenience wrappers.
* Tighten apps docs and widen content area
Strip editorial motivation from all app doc pages — let code examples
do the talking. Add content-area max-width override (44rem) to style.css.
* Restructure apps docs, fix code issues
Rename Prefab UI → Prefab Apps, mini-apps → patterns, remove
generative-uis and full-apps pages. Rewrite prefab page to lead with
what users do (declare a UI, return it) before explaining internals.
Patterns page now has fully self-contained copy-pasteable examples with
explicit imports and links to prefab docs. Forms show the two-tool
pattern (form + handler). Add patterns_server.py example.
Code fixes: move get_args to module-level import, remove dead
AuthCheckCallable type alias, fix ToolCall→CallTool in all docs.
* Remove unused ToolResult import from chart_server
* Handle composite Prefab types in type inference and schema suppression
_has_prefab_return_type and the output schema suppression logic only
checked bare classes, missing unions (Column | None) and Annotated
wrappers (Annotated[PrefabApp | None, ...]). Recurse through Union,
types.UnionType, and Annotated to detect Prefab types in composite
annotations.
* code mode
* update uv.lock for monty optional dep
🤖 Generated with Claude Code
* retry CI
* Address PR review comments on CodeMode transform
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Fix ty unresolved-attribute error on search_helper
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* more idiomacy
* harden
* fix docs
* harden
* fix red CI
* Refactor CodeMode to use CatalogTransform base class
Removes the duplicate ContextVar bypass pattern in favor of the shared
CatalogTransform machinery. Also fixes a pre-existing bug where
`from __future__ import annotations` caused NameError for Annotated
in nested function scopes at runtime.
* Remove redundant _get_visible_tools wrapper in CodeMode
* Rewrite CodeMode docs with proper motivation and structure
* Fix type narrowing in collision test
* Stop unwrapping tool results in CodeMode's call_tool
call_tool() inside execute blocks now returns structured content as-is,
preserving the {"result": value} wrapping. This means the output schema
shown in search results accurately describes what call_tool() returns,
so LLMs can trust the schema when writing code.
Also adds examples/code_mode/ with a server and narrated client demo.
* Simplify call_tool return type: dict | str
* Fix example client to unwrap structured results
* Let server resolve tool versions instead of pinning first match
* Rewrite CodeMode docs to match current behavior
* Rename optional extra from monty to code-mode
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Jeremiah Lowin <153965+jlowin@users.noreply.github.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 NameError with future annotations and Context/Depends parameters
Closes#3238, closes#905
* chore: Update SDK documentation
* Drop unnecessary pre-resolution of annotations
Pydantic (even 2.11.7) uses __module__ not __globals__ to resolve
annotations, so setting __module__ alone is sufficient.
* chore: Update SDK documentation
* Restore annotation pre-resolution for Pydantic compat
The wrapper's __globals__ is read-only and points to dependencies.py,
so some Pydantic versions use it instead of __module__ when resolving
string annotations. Pre-resolving via get_type_hints on the original
function ensures annotations are type objects before Pydantic sees them.
* chore: Update SDK documentation
---------
Co-authored-by: marvin-context-protocol[bot] <225465937+marvin-context-protocol[bot]@users.noreply.github.com>
* 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>
* Use standard traceparent/tracestate keys per OTel MCP semconv
The OTel semantic conventions for MCP (https://opentelemetry.io/docs/specs/semconv/gen-ai/mcp/)
put `traceparent` and `tracestate` directly in `params._meta` without a prefix.
FastMCP was using `fastmcp.traceparent` / `fastmcp.tracestate`, which meant
non-FastMCP clients sending the standard keys couldn't propagate traces.
Switches injection to the bare keys and adds fallback extraction for the old
prefixed keys so older FastMCP clients still work.
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: Update SDK documentation
* Drop legacy fastmcp.-prefixed trace key fallback
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: Update SDK documentation
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: marvin-context-protocol[bot] <225465937+marvin-context-protocol[bot]@users.noreply.github.com>
