* 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>
* Add upgrade guides for users coming from the MCP SDK
* Fix incorrect Image import path in LLM migration prompt
* Align LLM prompts with prose across all three upgrade guides
* Move upgrade guides under getting-started/upgrading, add install section and --upgrade flag
* 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>
* Reorganize docs navigation and add Apps documentation
Collapse Providers, Transforms, and Deployment under Servers. Add Apps
section with overview and low-level API pages. Add card images to welcome
page and README. Add NEW tags to recent features.
* Fix missing imports in Apps low-level API code examples
* Add `fastmcp generate-cli` command
Connects to any MCP server, reads its tool/resource/prompt schemas,
and writes a standalone Python CLI script with typed subcommands.
* docs: add generate-cli documentation
* docs: add generate-cli documentation; skip Windows executable test
* fix: address PR review feedback
- Sanitize tool and parameter names to valid Python identifiers
- Replace bare except Exception with specific exception types
- Escape server name in generated string literals
- Handle trailing colon edge case in _derive_server_name
- Clarify in docs that generated CLI is a client, not a bundled server
* Fix string escaping issues in generate-cli
- Use single-quoted docstrings to avoid triple-quote escaping issues
- Escape quotes in app_name derived from server_name
- Add tests for descriptions with quotes and server names with quotes
Addresses CodeRabbit review comments about insufficient escaping.
* Implement smart parameter handling for generate-cli
- Simple types (str, int, float, bool): Direct typed flags
- Arrays of simple types (list[str], list[int]): Repeatable flags via cyclopts
- Complex types (objects, nested arrays): Accept JSON strings with parsing
- JSON schema shown in help text for complex parameters
- Proper escaping of newlines and quotes in help text
- Filter out None and empty list defaults when calling tools
This gives typed, discoverable CLIs for common cases while handling
complex schemas via JSON input.
* Update generate-cli docs to explain smart parameter handling
- Document simple types as direct typed flags
- Document arrays of simple types as repeatable flags
- Document complex types as JSON strings with schema in help
- Add examples showing all three patterns
* Fix Codex review issues in generate-cli
High priority fixes:
- Complex type defaults: Serialize dict/list defaults to JSON strings
- List params: Preserve help metadata with Annotated wrapper
- Name collisions: Detect and error on sanitized name conflicts
- JSON parsing: Use isinstance check for safety with defaults
Added tests for:
- Complex types with default values
- Parameter name collision detection
- Updated existing tests to match new format
* Use pydantic_core.to_json for consistency
- Generator now uses pydantic_core.to_json() instead of json.dumps()
- Consistent with rest of fastmcp codebase
- Generated CLI still uses plain json module (standalone script)
* Move local imports to module level in generate-cli
* Handle union item types and Python keyword collisions in generate-cli
Rename Visibility to Enabled, collapse VisibilityRule into the transform,
and move enabled filtering from Provider to Server level so server-level
transforms can override provider-level disables.
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>
* Consolidate tool transformation logic into TransformingProvider
Tool transformations were previously scattered across LocalProvider,
ProxyProvider, and MCPConfig. This consolidates all transformation
logic into TransformingProvider via with_transforms(tool_transforms={...}).
- Add tool_transforms parameter to TransformingProvider
- Add tool_transforms to Provider.with_transforms()
- Remove transformation storage from LocalProvider and ProxyProvider
- Remove add_tool_transformation() and remove_tool_transformation() from FastMCP
- Add tool_transforms parameter to factory methods (from_openapi, from_fastapi, create_proxy)
- Update tests to use new patterns
* Fix: reject tool lookups by pre-transform name
* Add collision validation for tool_transforms and fix docstring examples
- Validate duplicate target names in tool_transforms raise ValueError
- Fix docstring examples to use arguments/ArgTransformConfig (not args/ArgTransform)
- Add test for collision validation
* Add server-level tool transform APIs and fix task registration
- Add AggregateProvider to present multiple providers as one
- Add _get_root_provider() to apply server-level transforms uniformly
- Fix _docket_lifespan to use root provider (ensures renamed tools
register with correct keys for background execution)
- Add tool_transforms kwarg to __init__ (non-deprecated)
- Add add_tool_transform(), remove_tool_transform(), tool_transforms property
- Deprecate old API names (tool_transformations, add_tool_transformation, etc.)
- Update tests to use new API
* Add graceful degradation for provider errors in AggregateProvider
* Match original behavior: parallel queries with DEBUG logging
* Refactor transforms to middleware-style call_next pattern
Replaces the ad-hoc transformation system with a unified Transform
abstraction using the same call_next pattern as server middleware.
Key changes:
- New src/fastmcp/server/transforms/ module with Transform base class
- Namespace, ToolTransform, Visibility all implement the same interface
- Transforms compose via functools.partial chain building
- Visibility is now just the first transform in provider._transforms
- Server-level transforms apply after provider aggregation
- Task registration now applies full transform chain
Removes TransformingProvider, _BoundTransform, ComponentSource protocol.
User-facing API unchanged: mount(), add_transform(), enable/disable all
work as before.
* Add comprehensive transforms and visibility documentation
New docs/servers/providers/transforms.mdx covering:
- Mental model for middleware-style transform pattern
- Built-in transforms (Namespace, ToolTransform)
- Server vs provider-level transforms and ordering
- Tool modification (immediate vs deferred)
- Custom transform creation
New docs/servers/visibility.mdx covering:
- Enable/disable API for runtime visibility control
- Keys and tags for targeting components
- Allowlist mode with only=True
- Server vs provider visibility layering
Updates existing docs to reference new pages and simplifies
redundant content. Visibility is documented as a user feature,
not as an implementation detail.
* Restructure transforms docs and delete tool-transformation pattern
* Cleanup: simplify get_tasks and remove unused Provider.get_component
* Update loq
* Update loq limits and add loq note to AGENTS.md
* Deprecate add_tool_transformation and tool_transformations param
* Address PR review feedback: remove redundant imports, fix path reference
* Add missing imports to code examples in v3-features.mdx
