local_provider

fastmcp.server.providers.local_provider

LocalProvider for locally-defined MCP components.

This module provides the LocalProvider class that manages tools, resources, templates, and prompts registered via decorators or direct methods.

LocalProvider can be used standalone and attached to multiple servers:

from fastmcp.server.providers import LocalProvider

# Create a reusable provider with tools
provider = LocalProvider()

@provider.tool
def greet(name: str) -> str:
    return f"Hello, {name}!"

# Attach to any server
from fastmcp import FastMCP
server1 = FastMCP("Server1", providers=[provider])
server2 = FastMCP("Server2", providers=[provider])

Classes

LocalProvider

Provider for locally-defined components.

Supports decorator-based registration (@provider.tool, @provider.resource, @provider.prompt) and direct object registration methods.

When used standalone, LocalProvider uses default settings. When attached to a FastMCP server via the server’s decorators, server-level settings like _tool_serializer and _support_tasks_by_default are injected.

Methods:

add_tool

add_tool(self, tool: Tool) -> Tool

Add a tool to this provider’s storage.

remove_tool

remove_tool(self, name: str) -> None

Remove a tool from this provider’s storage.

add_resource

add_resource(self, resource: Resource) -> Resource

Add a resource to this provider’s storage.

remove_resource

remove_resource(self, uri: str) -> None

Remove a resource from this provider’s storage.

add_template

add_template(self, template: ResourceTemplate) -> ResourceTemplate

Add a resource template to this provider’s storage.

remove_template

remove_template(self, uri_template: str) -> None

Remove a resource template from this provider’s storage.

add_prompt

add_prompt(self, prompt: Prompt) -> Prompt

Add a prompt to this provider’s storage.

remove_prompt

remove_prompt(self, name: str) -> None

Remove a prompt from this provider’s storage.

add_tool_transformation

add_tool_transformation(self, tool_name: str, transformation: ToolTransformConfig) -> None

Add a tool transformation.

Args:

• tool_name: The name of the tool to transform.
• transformation: The transformation configuration.

get_tool_transformation

get_tool_transformation(self, tool_name: str) -> ToolTransformConfig | None

Get a tool transformation.

Args:

• tool_name: The name of the tool.

Returns:

• The transformation config, or None if not found.

remove_tool_transformation

remove_tool_transformation(self, tool_name: str) -> None

Remove a tool transformation.

Args:

• tool_name: The name of the tool.

list_tools

list_tools(self) -> Sequence[Tool]

Return all visible tools with transformations applied.

get_tool

get_tool(self, name: str) -> Tool | None

Get a tool by name, with transformations applied.

list_resources

list_resources(self) -> Sequence[Resource]

Return all visible resources.

get_resource

get_resource(self, uri: str) -> Resource | None

Get a resource by URI if visible.

list_resource_templates

list_resource_templates(self) -> Sequence[ResourceTemplate]

Return all visible resource templates.

get_resource_template

get_resource_template(self, uri: str) -> ResourceTemplate | None

Get a resource template that matches the given URI if visible.

list_prompts

list_prompts(self) -> Sequence[Prompt]

Return all visible prompts.

get_prompt

get_prompt(self, name: str) -> Prompt | None

Get a prompt by name if visible.

get_component

get_component(self, key: str) -> Tool | Resource | ResourceTemplate | Prompt | None

Get a component by its prefixed key.

Efficient O(1) lookup in the unified components dict.

get_tasks

get_tasks(self) -> Sequence[FastMCPComponent]

Return components eligible for background task execution.

Returns components that have task_config.mode != ‘forbidden’. This includes both FunctionTool/Resource/Prompt instances created via decorators and custom Tool/Resource/Prompt subclasses.

tool

tool(self, name_or_fn: AnyFunction) -> FunctionTool

tool

tool(self, name_or_fn: str | None = None) -> Callable[[AnyFunction], FunctionTool]

tool

tool(self, name_or_fn: str | AnyFunction | None = None) -> Callable[[AnyFunction], FunctionTool] | FunctionTool | partial[Callable[[AnyFunction], FunctionTool] | FunctionTool]

Decorator to register a tool.

This decorator supports multiple calling patterns:

• @provider.tool (without parentheses)
• @provider.tool() (with empty parentheses)
• @provider.tool(“custom_name”) (with name as first argument)
• @provider.tool(name=“custom_name”) (with name as keyword argument)
• provider.tool(function, name=“custom_name”) (direct function call)

Args:

• name_or_fn: Either a function (when used as @tool), a string name, or None
• name: Optional name for the tool (keyword-only, alternative to name_or_fn)
• title: Optional title for the tool
• description: Optional description of what the tool does
• icons: Optional icons for the tool
• tags: Optional set of tags for categorizing the tool
• output_schema: Optional JSON schema for the tool’s output
• annotations: Optional annotations about the tool’s behavior
• exclude_args: Optional list of argument names to exclude from the tool schema
• meta: Optional meta information about the tool
• enabled: Whether the tool is enabled (default True). If False, adds to blocklist.
• task: Optional task configuration for background execution
• serializer: Deprecated. Return ToolResult from your tools for full control over serialization.

Returns:

• The registered FunctionTool or a decorator function.

resource

resource(self, uri: str) -> Callable[[AnyFunction], Resource | ResourceTemplate]

Decorator to register a function as a resource.

If the URI contains parameters (e.g. “resource://”) or the function has parameters, it will be registered as a template resource.

Args:

• uri: URI for the resource (e.g. “resource://my-resource” or “resource://”)
• name: Optional name for the resource
• title: Optional title for the resource
• description: Optional description of the resource
• icons: Optional icons for the resource
• mime_type: Optional MIME type for the resource
• tags: Optional set of tags for categorizing the resource
• enabled: Whether the resource is enabled (default True). If False, adds to blocklist.
• annotations: Optional annotations about the resource’s behavior
• meta: Optional meta information about the resource
• task: Optional task configuration for background execution

Returns:

• A decorator function.

prompt

prompt(self, name_or_fn: AnyFunction) -> FunctionPrompt

prompt

prompt(self, name_or_fn: str | None = None) -> Callable[[AnyFunction], FunctionPrompt]

prompt

prompt(self, name_or_fn: str | AnyFunction | None = None) -> Callable[[AnyFunction], FunctionPrompt] | FunctionPrompt | partial[Callable[[AnyFunction], FunctionPrompt] | FunctionPrompt]

Decorator to register a prompt.

This decorator supports multiple calling patterns:

• @provider.prompt (without parentheses)
• @provider.prompt() (with empty parentheses)
• @provider.prompt(“custom_name”) (with name as first argument)
• @provider.prompt(name=“custom_name”) (with name as keyword argument)
• provider.prompt(function, name=“custom_name”) (direct function call)

Args:

• name_or_fn: Either a function (when used as @prompt), a string name, or None
• name: Optional name for the prompt (keyword-only, alternative to name_or_fn)
• title: Optional title for the prompt
• description: Optional description of what the prompt does
• icons: Optional icons for the prompt
• tags: Optional set of tags for categorizing the prompt
• enabled: Whether the prompt is enabled (default True). If False, adds to blocklist.
• meta: Optional meta information about the prompt
• task: Optional task configuration for background execution

Returns:

• The registered FunctionPrompt or a decorator function.