- Add return type annotation to main() in run_with_tracing.py
- Use spread operator for argv construction
- Add type annotations to docs test example
- Use async httpx client and asyncio.sleep in diagnostics server
- Improve subprocess termination handling with timeout fallback
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Be specific about which operations are traced (tools, prompts, resources, resource templates)
- Remove "(not the SDK)" parenthetical
- Consolidate attribute documentation - remove redundancy in Tracing section
- Delete unnecessary examples/diagnostics/__init__.py
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds opt-in distributed tracing via OpenTelemetry for observability into
FastMCP server and client operations.
Server spans are created for tool calls, resource reads, and prompt
renders with attributes like component key, component type, provider
type, session ID, and auth context. Client spans wrap outgoing calls
with trace context propagation via W3C headers in request meta.
Components provide their own span attributes through a `get_span_attributes()`
method that subclasses override - this lets LocalProvider, FastMCPProvider,
and ProxyProvider each include relevant context (original names, backend URIs).
To enable: configure an OpenTelemetry SDK with a TracerProvider before
importing fastmcp. Traces export to any OTLP-compatible backend.
Closes ENG-2813
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add test_custom_subclass_tasks.py
* Refactor provider execution: delegate to middleware via wrapper components
- Remove execution methods (call_tool, read_resource, etc.) from Provider base
- Add FastMCPProvider* wrapper classes that delegate to child server middleware
- Move task routing to Tool._run() using contextvars (_task_metadata, _tool_call_key)
- Add convert_to_tool_result(result, output_schema) utility for Docket results
- Add convert_to_prompt_result() utility for prompt task results
- Pass namespaced key via add_to_docket(name=) for mounted tool lookup
* Standardize add_to_docket() with fn_key/task_key parameters
All components now use explicit fn_key (function lookup) and task_key
(result storage) parameters instead of relying on implicit key handling.
This fixes mounted component task execution where the MCP-visible key
differs from the Docket-registered function name.
* Add middleware chain tests for three-level mount hierarchy
Tests verify middleware runs at parent, child, and grandchild levels
for tools, resources, prompts, and resource templates.
* WIP: Provider refactor - unified submit_to_docket, template _read() in progress
Work in progress on refactoring execution to use component _read()/_run()/_render() methods.
Template background tasks not yet working - needs fix for Docket key lookup.
* Fix conversion functions to take full component for attribute access
Pass Tool/Prompt/Resource/Template to conversion functions instead of
individual attributes, ensuring access to serializer, output_schema,
mime_type, etc. Also fixes mixed-content output schema validation.
* Refactor: unified convert_result() methods and check_background_task helper
- Add convert_result() instance methods to all component types (Tool, Prompt, Resource, ResourceTemplate)
- Extract duplicated task routing logic into check_background_task() helper
- Fix type annotations on FastMCPProviderResource.read() and FastMCPProviderPrompt.render()
- Update protocol.py to use component.convert_result() uniformly
* Update tests to use namespace= instead of deprecated prefix= parameter
* Simplify Provider interface and consolidate docket registration
- Remove get_http_routes from Provider (unused)
- Remove ProviderLifespanConfig, _base_lifespan, _register_tasks
- Remove supports_tasks flag from Provider.__init__
- Consolidate all docket registration in server._docket_lifespan()
- Simplify lifespan() to take no parameters
- Move MountedProvider to separate module
* Fix control flow in ComponentService resource methods
* Move providers to server/providers
* Ensure MountedProvider get_* methods go through middleware
* Fix get_resource to only return concrete resources
Reverts template-checking in get_resource that broke task execution.
Tasks need access to the original template, not instantiated resources.
* Move prefix utilities into mounted.py, deprecate import_server
- Add resource prefix functions (add/remove/has_resource_prefix) to mounted.py
- Deprecate import_server with warning to use mount() instead
- Add tool_names uniqueness validation in MountedProvider
* Fix provider iteration order and remove dead _is_mounted flag
- Remove unused _is_mounted flag (MountedProvider.lifespan() calls _lifespan
not _lifespan_manager, so the flag was never checked)
- Fix provider iteration: change reversed() to forward order in execution
methods (_call_tool, _read_resource_middleware, _get_prompt_content_middleware)
to match documented "first non-None wins" semantics
- Fix ComponentService to handle prefix-less mounted servers using
_strip_tool_prefix()/_strip_resource_prefix() methods
- Update conflict resolution tests to expect first-registered provider wins
- Add regression tests for Docket behavior and prefix-less ComponentService
* Add TaskComponents type and exception handling for provider task registration
- Create TaskComponents dataclass with FunctionTool/FunctionResource/etc. types
for proper typing of get_tasks() return value
- Add try/except wrapper around provider.get_tasks() in _docket_lifespan for
consistent error handling (warn + continue or raise based on settings)
- Remove type: ignore comments from server.py task registration loop
* Fix tool_choice to always require tools when result_type is set
* Consolidate sampling examples with rich output
* Replace eval() with explicit add/multiply tools
* Unify SamplingHandler and promote OpenAI handler
Consolidates ServerSamplingHandler and ClientSamplingHandler into a single
SamplingHandler type alias. Moves OpenAISamplingHandler from experimental
to fastmcp.client.sampling.handlers.openai as the canonical location.
Backwards compatibility maintained for imports from experimental.
* Remove unreachable code paths in OpenAI handler
* Fix docstring and use elif for mutually exclusive branches
* MCP → SDK (vocab change only)
* WIP: Sampling API with SamplingResult[T] and result_type
* SEP-1577: Sampling with tools
- Add tools and result_type parameters to ctx.sample()
- Update OpenAI handler for tool content types
- Client advertises sampling.tools capability by default
- Collect tool results into single message with list content
* Fix tool result content handling in OpenAI handler
* Remove @sampling_tool decorator - pass functions directly to sample()
Functions passed to ctx.sample(tools=[...]) are now auto-converted
via SamplingTool.from_function(). Users can still use that method
directly for custom name/description overrides.
* Remove auto-conversion of MCP tools to sampling tools
Users want MCP tools passed to ctx.sample() to go through the full MCP
machinery (middleware, native responses) rather than being auto-converted
to direct function calls. Now only SamplingTool and plain callables are
accepted - passing a FastMCP Tool raises a clear TypeError.
Also bumps mcp dependency to >=1.24.0 for required sampling features.
* Refactor sampling API: replace sample_iter() with sample_step()
Replace the mutable SampleRun/sample_iter() pattern with a simpler stateless
sample_step() function. sample_step() makes a single LLM call and returns a
SampleStep with the response and history. sample() now loops sample_step()
internally.
Key changes:
- Add sample_step() for fine-grained control over the sampling loop
- Remove SampleRun class and sample_iter() method
- Structured output uses tool description only (no prompt modification)
- execute_tools parameter controls automatic vs manual tool execution
* Address CodeRabbit nitpicks
* Address CodeRabbit review feedback for sampling tools
- Fix temperature=0.0 being dropped due to falsy evaluation
- Add ToolChoice.name support for forcing specific tools
- Replace assert statements with explicit RuntimeError checks
- Add mask_error_details parameter to sample()/sample_step() with ToolError escape hatch
- Fix hasattr patterns with proper isinstance checks
- Document mask_error_details and add OpenAI prerequisites to docs
* Address additional CodeRabbit review feedback
- Catch ValidationError specifically instead of bare Exception
- Update result_type docs to mention dataclasses and basic types
- Raise ValueError for unknown tool_choice modes
- Validate sampling_handler_behavior to catch typos
- Remove ToolChoice.name handling (not part of MCP spec)
- Validate tool_choice string in sample_step()
* Review fixes for sampling tools PR
- Remove internal functions from sampling __init__.py exports
- Remove fragile is_text property, use not is_tool_use instead
- Inline call_client into context.py, remove from run.py
- Fix SamplingMessage docs to use TextContent
- Handle result.text being None in doc examples
- Simplify client sampling docs to recommend OpenAISamplingHandler
- Add sampling_capabilities override documentation
- Raise iteration limit from 50 to 100
- Remove _parse_model_preferences duplication
- Use AsyncOpenAI in OpenAISamplingHandler
- Fix tool_choice docstring
* Fix OpenAI handler tests to use AsyncOpenAI
* Address remaining CodeRabbit review comments
- Fix message ordering in OpenAI handler: tool results now correctly
follow assistant message with tool_calls
- sample_step() now always includes assistant message in history
- Raise ValueError on JSON parse errors instead of silent {}
- Add has_sampling capability check when behavior is None
- Raise RuntimeError when structured output receives text response
- Wrap primitive result_type schemas in object wrapper
- Fix docs example using invalid SamplingMessage construction
- Add comprehensive client_sampling_test.py example
* Add return type annotation to OpenAISamplingHandler.__init__
* Use explicit 'is not None' check for sampling_capabilities defaulting
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Bill Easton <strawgate@users.noreply.github.com>
The task protocol (SEP-1686) is now always enabled - server always
registers task handlers and advertises task capabilities. Users still
opt into background execution at the server level (tasks=True) or
component level (task=True on tools, prompts, resources).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
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
* 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
* 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>
- 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>
* 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
Changes settings.home from `Path.home() / ".fastmcp"` to use platformdirs.user_data_dir(), following platform conventions (~/Library/Application Support on macOS, ~/.local/share on Linux, %APPDATA% on Windows).
* Implement icon support in fastmcp
* Fix icon feature tests
- Update snapshot for ResourceTemplate to include icons field
- Remove OAuth mounting tests (belong to PR #2119, not this feature)
* Update docs
* Customize consent screen
* Use server website link if available
* Anchor link shouldnt have trailing slash
* Remove 'a FastMCP server named' from consent page message
* Update docs
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Ravi Madabhushi <ravi.madabhushi@scalekit.com>
Co-authored-by: Ravi Madabhushi <innovativeravi@gmail.com>
Co-authored-by: saif-at-scalekit <saif.shaik@scalekit.com>
