* Add EventStore and SSE polling support (SEP-1699)
* Add close_sse_stream() method to Context
* Add SSE polling documentation
* Fix missing Context import in docs example
* Remove EventStore from root __init__.py, update docs imports
- Removed EventStore import and export from src/fastmcp/__init__.py
- Updated docs to import EventStore from fastmcp.server.event_store
- Resolves merge conflict by not exporting EventStore from root package
Replace custom VersionBadge implementation with Mintlify's native Badge component while preserving custom color and border styling via CSS. This leverages Mintlify's built-in sizing, typography, and icon support while maintaining the original visual design.
- Lead with concepts instead of code
- Explain MCP background tasks vs general Python concurrency
- Document Docket's Prefect origins and battle-tested infrastructure
- Add sections on graceful degradation and embedded workers
- Fix version badge to 2.14.0
- Link to SEP-1686 spec
Docket provides background task execution and is now always available
for all FastMCP servers. Only `enable_tasks` remains to control the
SEP-1686 task protocol support.
Changes:
- Remove `enable_docket` setting and related validation
- Docket/Worker lifecycle is always active in server lifespan
- CurrentDocket and CurrentWorker dependencies work without config
- Add server readiness signaling via `_started` event
- Fix test timing issues with proper port probing
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Implement MCP background tasks (SEP-1686) using Docket
Adds support for background task execution via the MCP task protocol,
powered by Docket for task queue management.
- Tools, resources, and prompts can be marked with `task=True` to run async
- Progress dependency for tracking task progress
- CurrentDocket and CurrentWorker dependencies for advanced use cases
- Client API with `.call_tool(..., task=True)` returns task handles
- Task status notifications via subscriptions
- CLI worker command for distributed task processing
Configuration via environment:
- FASTMCP_ENABLE_DOCKET=true
- FASTMCP_ENABLE_TASKS=true
- FASTMCP_DOCKET_URL=redis://... (or memory:// for single-process)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix tasks example import (TaskStatusResponse → GetTaskResult)
The example was using a non-existent TaskStatusResponse type.
Updated to use mcp.types.GetTaskResult which is what the
on_status_change callback actually receives.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix env var name in Docket error messages
The error messages referenced FASTMCP_EXPERIMENTAL_ENABLE_DOCKET but the
actual setting is FASTMCP_ENABLE_DOCKET.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Remove deprecated code re-added from pre-#2329 branch
- Remove ExtendedEnvSettingsSource (FASTMCP_SERVER_ prefix support)
- Remove dependencies parameter from FastMCP.__init__
* Replace fakeredis git pin with PyPI release
* Remove redundant fakeredis dev dep (pulled via pydocket)
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Jeremiah Lowin <153965+jlowin@users.noreply.github.com>
* Fix RFC 8414 path-aware authorization server metadata discovery
Override get_well_known_routes() in OAuthProvider to rewrite the
authorization server metadata route to be path-aware based on issuer_url,
matching how protected resource metadata already works.
Closes#2527
* Update readme
* Initialize 2.14 deprecation removal branch
* Remove deprecated FASTMCP_SERVER_ environment variable prefix (#2330)
* Remove deprecated Context.get_http_request method (#2332)
* Remove fastmcp.Image top-level import (deprecated 2.8.1) (#2334)
* Remove test warnings (#2331)
* Create new branch and fix issue
* Remove deprecated client parameter from FastMCPProxy (#2333)
* Remove deprecated run_streamable_http_async method (#2338)
* Remove deprecated sse_app method (#2337)
* Remove deprecated run_sse_async method (#2335)
* Remove deprecated run_sse_async method
* Update CLI and tests to use run_http_async(transport="sse")
- Change CLI to call run_http_async with transport="sse" instead of run_sse_async
- Update test to mock run_http_async with create=True for v1 servers
* Revert CLI changes - v1 servers do have run_sse_async
- Keep CLI calling run_sse_async() for v1 compatibility
- Update test to mock run_sse_async (which exists on v1)
* Remove unnecessary type ignore for run_sse_async
Method exists on v1 FastMCP class, no type error
* Remove unused imports after test deletion
* Remove deprecated streamable_http_app method (#2336)
* Remove deprecated dependencies parameter from FastMCP constructor (#2340)
* Remove output_schema=False support (deprecated 2.11.4) (#2339)
* Remove deprecated client parameter from FastMCPProxy (#2333)
* Delete deprecated test_output_schema_false.py
Tests functionality that has been removed
* Remove deprecated BearerAuthProvider module (#2341)
* Remove resource_prefix_format="protocol" support (deprecated 2.4.0) (#2342)
* Remove resource_prefix_format="protocol" support (fixes#2195)
Removes deprecated protocol format (prefix+resource://path) and keeps only
path format (resource://prefix/path). Since only one format remains:
- Removed resource_prefix_format from settings, FastMCP.__init__, and helpers
- Simplified add_resource_prefix, remove_resource_prefix, has_resource_prefix
- Removed MountedServer.resource_prefix_format field
- Deleted tests for protocol format
All resource prefixes now use path format exclusively.
* Clean up resource_prefix_format references
- Remove from test files
- Update documentation to remove protocol format section
- Move custom HTTP routes note to mounting section
- Remove resource_prefix_format from settings docs
* Use inline version note instead of badge for prefix format
* Remove obsolete test functions and update docs
- Delete test functions that no longer assert anything
- Remove proxy.mdx reference to deleted prefix format section
* Format error messages per ruff
* Remove from_client classmethod (deprecated 2.8.0) (#2343)
* Remove deprecated from_client classmethod (fixes#2192)
* Remove unused Client import
* Remove add_resource_fn method (deprecated 2.7.0) (#2345)
* Update SDK
* Add missing imports for exclude_args deprecation warning
* Fix Azure provider to handle OIDC scopes correctly
OIDC scopes (openid, profile, email, offline_access) were being
incorrectly prefixed with identifier_uri, causing Azure to reject
authorization requests. This fix:
- Detects OIDC scopes and sends them unprefixed to Azure
- Filters OIDC scopes from token validation (Azure doesn't include
them in access token scp claims)
- Still advertises OIDC scopes to clients via valid_scopes
- Also handles dot-notation scopes (e.g., User.Read) correctly
Fixes#2451, #2420
* Fix dot-notation scopes to be prefixed (custom scopes can have dots)
* Improve Azure scope handling docs with clear examples
* Add consent_csp_policy parameter to OAuthProxy
Allows customization or disabling of CSP directives on the consent page.
Fixes#2476.
* Add consent_csp_policy to OIDCProxy and update docs
* Fix HTML injection vulnerability in CSP policy
HTML-escape the CSP policy value before inserting into meta tag to prevent HTML injection when CSP policies contain quotes.
Corrects the typo in the VersionBadge component in docs/servers/icons.mdx. The version number was incorrectly displayed as 2.14.0 but should be 2.13.0 to match the actual current version of FastMCP.
Fixes issue #2487
* sk-provider updates - aud not enforce, scopes enforce if present
* updating env_prefix, adding debug logs
* updating docs
* ruff formatting
* not changing prefix for backward compatiblity
* backward compatibility changes
* give more preference to base_url than mcp_url if both passed
* updating docs
* refactor
* updating example server
* updating readme of example
* updating docs
* updating tests to reflect what should ideally go in the parameter
Fixes issue #2431 where exclude_args fails when excluded parameters have
non-serializable types (e.g., ServerSession). The fix excludes parameters
from function annotations before Pydantic tries to serialize them.
Also adds deprecation notice that exclude_args will be deprecated in
FastMCP 2.14 in favor of dependency injection.
The on_initialize hook (2.13.0) runs before the MCP session is established, causing request_context
to be unavailable. Changed request_context to return None instead of raising, allowing middleware to
check availability and use HTTP helpers when needed. Updated docs to guide this pattern.
Closes#2393
* docs: clarify pytest-asyncio dependency and asyncio mode configuration
Added a Prerequisites section to the testing documentation explaining:
- pytest-asyncio is required for async test functions and fixtures
- Recommended configuration: asyncio_mode = 'auto' in pyproject.toml
- This eliminates need for @pytest.mark.asyncio decorators
Resolves#2372
Co-authored-by: William Easton <strawgate@users.noreply.github.com>
* feat: add testing_demo example with comprehensive test suite
Add a standalone example project demonstrating FastMCP testing patterns:
- Tools, resources, and prompts with full test coverage
- pytest-asyncio configuration in pyproject.toml
- 18 passing tests showing async fixtures, parametrized tests, and more
- Documentation explaining testing best practices
Co-authored-by: William Easton <strawgate@users.noreply.github.com>
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: William Easton <strawgate@users.noreply.github.com>
* Add manual initialization control to Client
- Add auto_initialize parameter (default True) to control automatic initialization
- Make initialize() method public with idempotent caching
- Add comprehensive test suite for initialization behavior
* Document client initialization control and server instructions
- Expand documentation to cover auto_initialize parameter
- Show manual initialization for advanced use cases
- Document accessing server instructions via initialize_result
* Update client.mdx
* switch from pre-commit to prek
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix prek tools list in contributing.mdx - include prettier, not pytest
* Use prek-action for caching
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Jeremiah Lowin <153965+jlowin@users.noreply.github.com>
- Restructured confusing sections: 'Object-like Results' → 'Dictionaries and Objects', 'Non-object Results' → 'Primitives and Collections', 'Complex Type Example' → 'Typed Models'
- Simplified CodeGroup examples to show Tool Definition + MCP Result instead of 3-4 confusing tabs
- Split Primitives/Collections into separate CodeGroups for clarity
- Renamed 'Full Control with ToolResult' → 'ToolResult and Metadata' for better TOC visibility
- Flattened ToolResult documentation with inline field descriptions instead of nested headings
- Added version badge for ToolResult meta field (2.13.1)
- Added clarification that ToolResult meta is separate from @mcp.tool meta
- Improved example server with realistic metadata (execution time, character/word counts)
- Fixed code formatting (multi-line objects, trailing commas)
* Add meta to ToolResult
* add this at the client level and test the full integration
* add example
* slipped through linting somehow
---------
Co-authored-by: Jeremiah Lowin <153965+jlowin@users.noreply.github.com>
* Added to_data_uri method and path_to_data_uri classmethod for Image class.
* Removed path_to_data_uri classmethod and modified _get_mime_type to use mimetypes.guess_type function instead of hardcoded dictionary.
* Register image/webp with mimetypes before guess_type to support WEBP mimetype detection on Python 3.10.
* Improved branch coverage for Image.to_data_uri.
* Added Image._to_data_uri example in the docs.
Add warning notes to documentation directing users to review
py-key-value documentation for backend maturity and limitations
before production use.
Co-authored-by: William Easton <strawgate@users.noreply.github.com>
* Add custom token verifier support to OIDCProxy
OIDCProxy now accepts an optional token_verifier parameter to support
non-JWT token formats like opaque tokens from providers such as Clerk.
When provided, the custom verifier is used instead of creating a default
JWTVerifier. Parameters that only apply to JWTVerifier creation (algorithm,
required_scopes) raise clear errors when specified alongside a custom
verifier. Parameters with other purposes (audience for OAuth flow,
timeout_seconds for config fetch) remain allowed.
The custom verifier's required_scopes are automatically loaded and
advertised through OAuth discovery endpoints.
* Document custom token verifier support in OIDC proxy
* Update docs for required scopes
* add scopes
* Fix Azure scope validation
Azure returns unprefixed scopes in JWT tokens but requires prefixed scopes in authorization requests. The previous implementation incorrectly validated tokens against prefixed scopes, causing "invalid_token" errors.
Simplified AzureProvider to use standard JWTVerifier with unprefixed scopes for validation. Scopes are only prefixed when building the Azure authorization URL via _build_upstream_authorize_url() override.
Closes#2263
* Improve OAuth client token storage security documentation
Updated warning message and documentation to address security concerns
around storing OAuth credentials for multiple MCP servers.
