- MCP Python SDK
The Model Context Protocol allows applications to provide context for LLMs in a standardized way, separating the concerns of providing context from the actual LLM interaction. This Python SDK implements the full MCP specification, making it easy to:
- Build MCP clients that can connect to any MCP server
- Create MCP servers that expose resources, prompts and tools
- Use standard transports like stdio, SSE, and Streamable HTTP
- Handle all MCP protocol messages and lifecycle events
We recommend using uv to manage your Python projects.
If you haven't created a uv-managed project yet, create one:
uv init mcp-server-demo cd mcp-server-demoThen add MCP to your project dependencies:
uv add "mcp[cli]"Alternatively, for projects using pip for dependencies:
pip install "mcp[cli]"To run the mcp command with uv:
uv run mcpLet's create a simple MCP server that exposes a calculator tool and some data:
"""FastMCP quickstart example.Run from the repository root: uv run examples/snippets/servers/fastmcp_quickstart.py"""frommcp.server.fastmcpimportFastMCP# Create an MCP servermcp=FastMCP("Demo", json_response=True) # Add an addition tool@mcp.tool()defadd(a: int, b: int) ->int: """Add two numbers"""returna+b# Add a dynamic greeting resource@mcp.resource("greeting://{name}")defget_greeting(name: str) ->str: """Get a personalized greeting"""returnf"Hello, {name}!"# Add a prompt@mcp.prompt()defgreet_user(name: str, style: str="friendly") ->str: """Generate a greeting prompt"""styles={"friendly": "Please write a warm, friendly greeting", "formal": "Please write a formal, professional greeting", "casual": "Please write a casual, relaxed greeting", } returnf"{styles.get(style, styles['friendly'])} for someone named {name}."# Run with streamable HTTP transportif__name__=="__main__": mcp.run(transport="streamable-http")Full example: examples/snippets/servers/fastmcp_quickstart.py
You can install this server in Claude Code and interact with it right away. First, run the server:
uv run --with mcp examples/snippets/servers/fastmcp_quickstart.pyThen add it to Claude Code:
claude mcp add --transport http my-server http://localhost:8000/mcpAlternatively, you can test it with the MCP Inspector. Start the server as above, then in a separate terminal:
npx -y @modelcontextprotocol/inspectorIn the inspector UI, connect to http://localhost:8000/mcp.
The Model Context Protocol (MCP) lets you build servers that expose data and functionality to LLM applications in a secure, standardized way. Think of it like a web API, but specifically designed for LLM interactions. MCP servers can:
- Expose data through Resources (think of these sort of like GET endpoints; they are used to load information into the LLM's context)
- Provide functionality through Tools (sort of like POST endpoints; they are used to execute code or otherwise produce a side effect)
- Define interaction patterns through Prompts (reusable templates for LLM interactions)
- And more!
The FastMCP server is your core interface to the MCP protocol. It handles connection management, protocol compliance, and message routing:
"""Example showing lifespan support for startup/shutdown with strong typing."""fromcollections.abcimportAsyncIteratorfromcontextlibimportasynccontextmanagerfromdataclassesimportdataclassfrommcp.server.fastmcpimportContext, FastMCPfrommcp.server.sessionimportServerSession# Mock database class for exampleclassDatabase: """Mock database class for example."""@classmethodasyncdefconnect(cls) ->"Database": """Connect to database."""returncls() asyncdefdisconnect(self) ->None: """Disconnect from database."""passdefquery(self) ->str: """Execute a query."""return"Query result"@dataclassclassAppContext: """Application context with typed dependencies."""db: Database@asynccontextmanagerasyncdefapp_lifespan(server: FastMCP) ->AsyncIterator[AppContext]: """Manage application lifecycle with type-safe context."""# Initialize on startupdb=awaitDatabase.connect() try: yieldAppContext(db=db) finally: # Cleanup on shutdownawaitdb.disconnect() # Pass lifespan to servermcp=FastMCP("My App", lifespan=app_lifespan) # Access type-safe lifespan context in tools@mcp.tool()defquery_db(ctx: Context[ServerSession, AppContext]) ->str: """Tool that uses initialized resources."""db=ctx.request_context.lifespan_context.dbreturndb.query()Full example: examples/snippets/servers/lifespan_example.py
Resources are how you expose data to LLMs. They're similar to GET endpoints in a REST API - they provide data but shouldn't perform significant computation or have side effects:
frommcp.server.fastmcpimportFastMCPmcp=FastMCP(name="Resource Example") @mcp.resource("file://documents/{name}")defread_document(name: str) ->str: """Read a document by name."""# This would normally read from diskreturnf"Content of {name}"@mcp.resource("config://settings")defget_settings() ->str: """Get application settings."""return"""{ "theme": "dark", "language": "en", "debug": false}"""Full example: examples/snippets/servers/basic_resource.py
Tools let LLMs take actions through your server. Unlike resources, tools are expected to perform computation and have side effects:
frommcp.server.fastmcpimportFastMCPmcp=FastMCP(name="Tool Example") @mcp.tool()defsum(a: int, b: int) ->int: """Add two numbers together."""returna+b@mcp.tool()defget_weather(city: str, unit: str="celsius") ->str: """Get weather for a city."""# This would normally call a weather APIreturnf"Weather in {city}: 22degrees{unit[0].upper()}"Full example: examples/snippets/servers/basic_tool.py
Tools can optionally receive a Context object by including a parameter with the Context type annotation. This context is automatically injected by the FastMCP framework and provides access to MCP capabilities:
frommcp.server.fastmcpimportContext, FastMCPfrommcp.server.sessionimportServerSessionmcp=FastMCP(name="Progress Example") @mcp.tool()asyncdeflong_running_task(task_name: str, ctx: Context[ServerSession, None], steps: int=5) ->str: """Execute a task with progress updates."""awaitctx.info(f"Starting: {task_name}") foriinrange(steps): progress= (i+1) /stepsawaitctx.report_progress( progress=progress, total=1.0, message=f"Step {i+1}/{steps}", ) awaitctx.debug(f"Completed step {i+1}") returnf"Task '{task_name}' completed"Full example: examples/snippets/servers/tool_progress.py
Tools will return structured results by default, if their return type annotation is compatible. Otherwise, they will return unstructured results.
Structured output supports these return types:
- Pydantic models (BaseModel subclasses)
- TypedDicts
- Dataclasses and other classes with type hints
dict[str, T](where T is any JSON-serializable type)- Primitive types (str, int, float, bool, bytes, None) - wrapped in
{"result": value} - Generic types (list, tuple, Union, Optional, etc.) - wrapped in
{"result": value}
Classes without type hints cannot be serialized for structured output. Only classes with properly annotated attributes will be converted to Pydantic models for schema generation and validation.
Structured results are automatically validated against the output schema generated from the annotation. This ensures the tool returns well-typed, validated data that clients can easily process.
Note: For backward compatibility, unstructured results are also returned. Unstructured results are provided for backward compatibility with previous versions of the MCP specification, and are quirks-compatible with previous versions of FastMCP in the current version of the SDK.
Note: In cases where a tool function's return type annotation causes the tool to be classified as structured and this is undesirable, the classification can be suppressed by passing structured_output=False to the @tool decorator.
For full control over tool responses including the _meta field (for passing data to client applications without exposing it to the model), you can return CallToolResult directly:
"""Example showing direct CallToolResult return for advanced control."""fromtypingimportAnnotatedfrompydanticimportBaseModelfrommcp.server.fastmcpimportFastMCPfrommcp.typesimportCallToolResult, TextContentmcp=FastMCP("CallToolResult Example") classValidationModel(BaseModel): """Model for validating structured output."""status: strdata: dict[str, int] @mcp.tool()defadvanced_tool() ->CallToolResult: """Return CallToolResult directly for full control including _meta field."""returnCallToolResult( content=[TextContent(type="text", text="Response visible to the model")], _meta={"hidden": "data for client applications only"}, ) @mcp.tool()defvalidated_tool() ->Annotated[CallToolResult, ValidationModel]: """Return CallToolResult with structured output validation."""returnCallToolResult( content=[TextContent(type="text", text="Validated response")], structuredContent={"status": "success", "data":{"result": 42}}, _meta={"internal": "metadata"}, ) @mcp.tool()defempty_result_tool() ->CallToolResult: """For empty results, return CallToolResult with empty content."""returnCallToolResult(content=[])Full example: examples/snippets/servers/direct_call_tool_result.py
Important:CallToolResult must always be returned (no Optional or Union). For empty results, use CallToolResult(content=[]). For optional simple types, use str | None without CallToolResult.
"""Example showing structured output with tools."""fromtypingimportTypedDictfrompydanticimportBaseModel, Fieldfrommcp.server.fastmcpimportFastMCPmcp=FastMCP("Structured Output Example") # Using Pydantic models for rich structured dataclassWeatherData(BaseModel): """Weather information structure."""temperature: float=Field(description="Temperature in Celsius") humidity: float=Field(description="Humidity percentage") condition: strwind_speed: float@mcp.tool()defget_weather(city: str) ->WeatherData: """Get weather for a city - returns structured data."""# Simulated weather datareturnWeatherData( temperature=22.5, humidity=45.0, condition="sunny", wind_speed=5.2, ) # Using TypedDict for simpler structuresclassLocationInfo(TypedDict): latitude: floatlongitude: floatname: str@mcp.tool()defget_location(address: str) ->LocationInfo: """Get location coordinates"""returnLocationInfo(latitude=51.5074, longitude=-0.1278, name="London, UK") # Using dict[str, Any] for flexible schemas@mcp.tool()defget_statistics(data_type: str) ->dict[str, float]: """Get various statistics"""return{"mean": 42.5, "median": 40.0, "std_dev": 5.2} # Ordinary classes with type hints work for structured outputclassUserProfile: name: strage: intemail: str|None=Nonedef__init__(self, name: str, age: int, email: str|None=None): self.name=nameself.age=ageself.email=email@mcp.tool()defget_user(user_id: str) ->UserProfile: """Get user profile - returns structured data"""returnUserProfile(name="Alice", age=30, email="[email protected]") # Classes WITHOUT type hints cannot be used for structured outputclassUntypedConfig: def__init__(self, setting1, setting2): # type: ignore[reportMissingParameterType]self.setting1=setting1self.setting2=setting2@mcp.tool()defget_config() ->UntypedConfig: """This returns unstructured output - no schema generated"""returnUntypedConfig("value1", "value2") # Lists and other types are wrapped automatically@mcp.tool()deflist_cities() ->list[str]: """Get a list of cities"""return ["London", "Paris", "Tokyo"] # Returns:{"result": ["London", "Paris", "Tokyo"]}@mcp.tool()defget_temperature(city: str) ->float: """Get temperature as a simple float"""return22.5# Returns:{"result": 22.5}Full example: examples/snippets/servers/structured_output.py
Prompts are reusable templates that help LLMs interact with your server effectively:
frommcp.server.fastmcpimportFastMCPfrommcp.server.fastmcp.promptsimportbasemcp=FastMCP(name="Prompt Example") @mcp.prompt(title="Code Review")defreview_code(code: str) ->str: returnf"Please review this code:\n\n{code}"@mcp.prompt(title="Debug Assistant")defdebug_error(error: str) ->list[base.Message]: return [ base.UserMessage("I'm seeing this error:"), base.UserMessage(error), base.AssistantMessage("I'll help debug that. What have you tried so far?"), ]Full example: examples/snippets/servers/basic_prompt.py
MCP servers can provide icons for UI display. Icons can be added to the server implementation, tools, resources, and prompts:
frommcp.server.fastmcpimportFastMCP, Icon# Create an icon from a file path or URLicon=Icon( src="icon.png", mimeType="image/png", sizes="64x64" ) # Add icons to servermcp=FastMCP( "My Server", website_url="https://example.com", icons=[icon] ) # Add icons to tools, resources, and prompts@mcp.tool(icons=[icon])defmy_tool(): """Tool with an icon."""return"result"@mcp.resource("demo://resource", icons=[icon])defmy_resource(): """Resource with an icon."""return"content"Full example: examples/fastmcp/icons_demo.py
FastMCP provides an Image class that automatically handles image data:
"""Example showing image handling with FastMCP."""fromPILimportImageasPILImagefrommcp.server.fastmcpimportFastMCP, Imagemcp=FastMCP("Image Example") @mcp.tool()defcreate_thumbnail(image_path: str) ->Image: """Create a thumbnail from an image"""img=PILImage.open(image_path) img.thumbnail((100, 100)) returnImage(data=img.tobytes(), format="png")Full example: examples/snippets/servers/images.py
The Context object is automatically injected into tool and resource functions that request it via type hints. It provides access to MCP capabilities like logging, progress reporting, resource reading, user interaction, and request metadata.
To use context in a tool or resource function, add a parameter with the Context type annotation:
frommcp.server.fastmcpimportContext, FastMCPmcp=FastMCP(name="Context Example") @mcp.tool()asyncdefmy_tool(x: int, ctx: Context) ->str: """Tool that uses context capabilities."""# The context parameter can have any name as long as it's type-annotatedreturnawaitprocess_with_context(x, ctx)The Context object provides the following capabilities:
ctx.request_id- Unique ID for the current requestctx.client_id- Client ID if availablectx.fastmcp- Access to the FastMCP server instance (see FastMCP Properties)ctx.session- Access to the underlying session for advanced communication (see Session Properties and Methods)ctx.request_context- Access to request-specific data and lifespan resources (see Request Context Properties)await ctx.debug(message)- Send debug log messageawait ctx.info(message)- Send info log messageawait ctx.warning(message)- Send warning log messageawait ctx.error(message)- Send error log messageawait ctx.log(level, message, logger_name=None)- Send log with custom levelawait ctx.report_progress(progress, total=None, message=None)- Report operation progressawait ctx.read_resource(uri)- Read a resource by URIawait ctx.elicit(message, schema)- Request additional information from user with validation
frommcp.server.fastmcpimportContext, FastMCPfrommcp.server.sessionimportServerSessionmcp=FastMCP(name="Progress Example") @mcp.tool()asyncdeflong_running_task(task_name: str, ctx: Context[ServerSession, None], steps: int=5) ->str: """Execute a task with progress updates."""awaitctx.info(f"Starting: {task_name}") foriinrange(steps): progress= (i+1) /stepsawaitctx.report_progress( progress=progress, total=1.0, message=f"Step {i+1}/{steps}", ) awaitctx.debug(f"Completed step {i+1}") returnf"Task '{task_name}' completed"Full example: examples/snippets/servers/tool_progress.py
MCP supports providing completion suggestions for prompt arguments and resource template parameters. With the context parameter, servers can provide completions based on previously resolved values:
Client usage:
"""cd to the `examples/snippets` directory and run: uv run completion-client"""importasyncioimportosfrommcpimportClientSession, StdioServerParametersfrommcp.client.stdioimportstdio_clientfrommcp.typesimportPromptReference, ResourceTemplateReference# Create server parameters for stdio connectionserver_params=StdioServerParameters( command="uv", # Using uv to run the serverargs=["run", "server", "completion", "stdio"], # Server with completion supportenv={"UV_INDEX": os.environ.get("UV_INDEX", "")}, ) asyncdefrun(): """Run the completion client example."""asyncwithstdio_client(server_params) as (read, write): asyncwithClientSession(read, write) assession: # Initialize the connectionawaitsession.initialize() # List available resource templatestemplates=awaitsession.list_resource_templates() print("Available resource templates:") fortemplateintemplates.resourceTemplates: print(f" - {template.uriTemplate}") # List available promptsprompts=awaitsession.list_prompts() print("\nAvailable prompts:") forpromptinprompts.prompts: print(f" - {prompt.name}") # Complete resource template argumentsiftemplates.resourceTemplates: template=templates.resourceTemplates[0] print(f"\nCompleting arguments for resource template: {template.uriTemplate}") # Complete without contextresult=awaitsession.complete( ref=ResourceTemplateReference(type="ref/resource", uri=template.uriTemplate), argument={"name": "owner", "value": "model"}, ) print(f"Completions for 'owner' starting with 'model': {result.completion.values}") # Complete with context - repo suggestions based on ownerresult=awaitsession.complete( ref=ResourceTemplateReference(type="ref/resource", uri=template.uriTemplate), argument={"name": "repo", "value": ""}, context_arguments={"owner": "modelcontextprotocol"}, ) print(f"Completions for 'repo' with owner='modelcontextprotocol': {result.completion.values}") # Complete prompt argumentsifprompts.prompts: prompt_name=prompts.prompts[0].nameprint(f"\nCompleting arguments for prompt: {prompt_name}") result=awaitsession.complete( ref=PromptReference(type="ref/prompt", name=prompt_name), argument={"name": "style", "value": ""}, ) print(f"Completions for 'style' argument: {result.completion.values}") defmain(): """Entry point for the completion client."""asyncio.run(run()) if__name__=="__main__": main()Full example: examples/snippets/clients/completion_client.py
Request additional information from users. This example shows an Elicitation during a Tool Call:
"""Elicitation examples demonstrating form and URL mode elicitation.Form mode elicitation collects structured, non-sensitive data through a schema.URL mode elicitation directs users to external URLs for sensitive operationslike OAuth flows, credential collection, or payment processing."""importuuidfrompydanticimportBaseModel, Fieldfrommcp.server.fastmcpimportContext, FastMCPfrommcp.server.sessionimportServerSessionfrommcp.shared.exceptionsimportUrlElicitationRequiredErrorfrommcp.typesimportElicitRequestURLParamsmcp=FastMCP(name="Elicitation Example") classBookingPreferences(BaseModel): """Schema for collecting user preferences."""checkAlternative: bool=Field(description="Would you like to check another date?") alternativeDate: str=Field( default="2024-12-26", description="Alternative date (YYYY-MM-DD)", ) @mcp.tool()asyncdefbook_table(date: str, time: str, party_size: int, ctx: Context[ServerSession, None]) ->str: """Book a table with date availability check. This demonstrates form mode elicitation for collecting non-sensitive user input. """# Check if date is availableifdate=="2024-12-25": # Date unavailable - ask user for alternativeresult=awaitctx.elicit( message=(f"No tables available for {party_size} on {date}. Would you like to try another date?"), schema=BookingPreferences, ) ifresult.action=="accept"andresult.data: ifresult.data.checkAlternative: returnf"[SUCCESS] Booked for {result.data.alternativeDate}"return"[CANCELLED] No booking made"return"[CANCELLED] Booking cancelled"# Date availablereturnf"[SUCCESS] Booked for {date} at {time}"@mcp.tool()asyncdefsecure_payment(amount: float, ctx: Context[ServerSession, None]) ->str: """Process a secure payment requiring URL confirmation. This demonstrates URL mode elicitation using ctx.elicit_url() for operations that require out-of-band user interaction. """elicitation_id=str(uuid.uuid4()) result=awaitctx.elicit_url( message=f"Please confirm payment of ${amount:.2f}", url=f"https://payments.example.com/confirm?amount={amount}&id={elicitation_id}", elicitation_id=elicitation_id, ) ifresult.action=="accept": # In a real app, the payment confirmation would happen out-of-band# and you'd verify the payment status from your backendreturnf"Payment of ${amount:.2f} initiated - check your browser to complete"elifresult.action=="decline": return"Payment declined by user"return"Payment cancelled"@mcp.tool()asyncdefconnect_service(service_name: str, ctx: Context[ServerSession, None]) ->str: """Connect to a third-party service requiring OAuth authorization. This demonstrates the "throw error" pattern using UrlElicitationRequiredError. Use this pattern when the tool cannot proceed without user authorization. """elicitation_id=str(uuid.uuid4()) # Raise UrlElicitationRequiredError to signal that the client must complete# a URL elicitation before this request can be processed.# The MCP framework will convert this to a -32042 error response.raiseUrlElicitationRequiredError( [ ElicitRequestURLParams( mode="url", message=f"Authorization required to connect to {service_name}", url=f"https://{service_name}.example.com/oauth/authorize?elicit={elicitation_id}", elicitationId=elicitation_id, ) ] )Full example: examples/snippets/servers/elicitation.py
Elicitation schemas support default values for all field types. Default values are automatically included in the JSON schema sent to clients, allowing them to pre-populate forms.
The elicit() method returns an ElicitationResult with:
action: "accept", "decline", or "cancel"data: The validated response (only when accepted)validation_error: Any validation error message
Tools can interact with LLMs through sampling (generating text):
frommcp.server.fastmcpimportContext, FastMCPfrommcp.server.sessionimportServerSessionfrommcp.typesimportSamplingMessage, TextContentmcp=FastMCP(name="Sampling Example") @mcp.tool()asyncdefgenerate_poem(topic: str, ctx: Context[ServerSession, None]) ->str: """Generate a poem using LLM sampling."""prompt=f"Write a short poem about {topic}"result=awaitctx.session.create_message( messages=[ SamplingMessage( role="user", content=TextContent(type="text", text=prompt), ) ], max_tokens=100, ) # Since we're not passing tools param, result.content is single contentifresult.content.type=="text": returnresult.content.textreturnstr(result.content)Full example: examples/snippets/servers/sampling.py
Tools can send logs and notifications through the context:
frommcp.server.fastmcpimportContext, FastMCPfrommcp.server.sessionimportServerSessionmcp=FastMCP(name="Notifications Example") @mcp.tool()asyncdefprocess_data(data: str, ctx: Context[ServerSession, None]) ->str: """Process data with logging."""# Different log levelsawaitctx.debug(f"Debug: Processing '{data}'") awaitctx.info("Info: Starting processing") awaitctx.warning("Warning: This is experimental") awaitctx.error("Error: (This is just a demo)") # Notify about resource changesawaitctx.session.send_resource_list_changed() returnf"Processed: {data}"Full example: examples/snippets/servers/notifications.py
Authentication can be used by servers that want to expose tools accessing protected resources.
mcp.server.auth implements OAuth 2.1 resource server functionality, where MCP servers act as Resource Servers (RS) that validate tokens issued by separate Authorization Servers (AS). This follows the MCP authorization specification and implements RFC 9728 (Protected Resource Metadata) for AS discovery.
MCP servers can use authentication by providing an implementation of the TokenVerifier protocol:
"""Run from the repository root: uv run examples/snippets/servers/oauth_server.py"""frompydanticimportAnyHttpUrlfrommcp.server.auth.providerimportAccessToken, TokenVerifierfrommcp.server.auth.settingsimportAuthSettingsfrommcp.server.fastmcpimportFastMCPclassSimpleTokenVerifier(TokenVerifier): """Simple token verifier for demonstration."""asyncdefverify_token(self, token: str) ->AccessToken|None: pass# This is where you would implement actual token validation# Create FastMCP instance as a Resource Servermcp=FastMCP( "Weather Service", json_response=True, # Token verifier for authenticationtoken_verifier=SimpleTokenVerifier(), # Auth settings for RFC 9728 Protected Resource Metadataauth=AuthSettings( issuer_url=AnyHttpUrl("https://auth.example.com"), # Authorization Server URLresource_server_url=AnyHttpUrl("http://localhost:3001"), # This server's URLrequired_scopes=["user"], ), ) @mcp.tool()asyncdefget_weather(city: str="London") ->dict[str, str]: """Get weather data for a city"""return{"city": city, "temperature": "22", "condition": "Partly cloudy", "humidity": "65%", } if__name__=="__main__": mcp.run(transport="streamable-http")Full example: examples/snippets/servers/oauth_server.py
For a complete example with separate Authorization Server and Resource Server implementations, see examples/servers/simple-auth/.
Architecture:
- Authorization Server (AS): Handles OAuth flows, user authentication, and token issuance
- Resource Server (RS): Your MCP server that validates tokens and serves protected resources
- Client: Discovers AS through RFC 9728, obtains tokens, and uses them with the MCP server
See TokenVerifier for more details on implementing token validation.
The FastMCP server instance accessible via ctx.fastmcp provides access to server configuration and metadata:
ctx.fastmcp.name- The server's name as defined during initializationctx.fastmcp.instructions- Server instructions/description provided to clientsctx.fastmcp.website_url- Optional website URL for the serverctx.fastmcp.icons- Optional list of icons for UI displayctx.fastmcp.settings- Complete server configuration object containing:debug- Debug mode flaglog_level- Current logging levelhostandport- Server network configurationmount_path,sse_path,streamable_http_path- Transport pathsstateless_http- Whether the server operates in stateless mode- And other configuration options
@mcp.tool()defserver_info(ctx: Context) ->dict: """Get information about the current server."""return{"name": ctx.fastmcp.name, "instructions": ctx.fastmcp.instructions, "debug_mode": ctx.fastmcp.settings.debug, "log_level": ctx.fastmcp.settings.log_level, "host": ctx.fastmcp.settings.host, "port": ctx.fastmcp.settings.port, }The session object accessible via ctx.session provides advanced control over client communication:
ctx.session.client_params- Client initialization parameters and declared capabilitiesawait ctx.session.send_log_message(level, data, logger)- Send log messages with full controlawait ctx.session.create_message(messages, max_tokens)- Request LLM sampling/completionawait ctx.session.send_progress_notification(token, progress, total, message)- Direct progress updatesawait ctx.session.send_resource_updated(uri)- Notify clients that a specific resource changedawait ctx.session.send_resource_list_changed()- Notify clients that the resource list changedawait ctx.session.send_tool_list_changed()- Notify clients that the tool list changedawait ctx.session.send_prompt_list_changed()- Notify clients that the prompt list changed
@mcp.tool()asyncdefnotify_data_update(resource_uri: str, ctx: Context) ->str: """Update data and notify clients of the change."""# Perform data update logic here# Notify clients that this specific resource changedawaitctx.session.send_resource_updated(AnyUrl(resource_uri)) # If this affects the overall resource list, notify about that tooawaitctx.session.send_resource_list_changed() returnf"Updated {resource_uri} and notified clients"The request context accessible via ctx.request_context contains request-specific information and resources:
ctx.request_context.lifespan_context- Access to resources initialized during server startup- Database connections, configuration objects, shared services
- Type-safe access to resources defined in your server's lifespan function
ctx.request_context.meta- Request metadata from the client including:progressToken- Token for progress notifications- Other client-provided metadata
ctx.request_context.request- The original MCP request object for advanced processingctx.request_context.request_id- Unique identifier for this request
# Example with typed lifespan context@dataclassclassAppContext: db: Databaseconfig: AppConfig@mcp.tool()defquery_with_config(query: str, ctx: Context) ->str: """Execute a query using shared database and configuration."""# Access typed lifespan contextapp_ctx: AppContext=ctx.request_context.lifespan_context# Use shared resourcesconnection=app_ctx.dbsettings=app_ctx.config# Execute query with configurationresult=connection.execute(query, timeout=settings.query_timeout) returnstr(result)Full lifespan example: examples/snippets/servers/lifespan_example.py
The fastest way to test and debug your server is with the MCP Inspector:
uv run mcp dev server.py # Add dependencies uv run mcp dev server.py --with pandas --with numpy # Mount local code uv run mcp dev server.py --with-editable .Once your server is ready, install it in Claude Desktop:
uv run mcp install server.py # Custom name uv run mcp install server.py --name "My Analytics Server"# Environment variables uv run mcp install server.py -v API_KEY=abc123 -v DB_URL=postgres://... uv run mcp install server.py -f .envFor advanced scenarios like custom deployments:
"""Example showing direct execution of an MCP server.This is the simplest way to run an MCP server directly.cd to the `examples/snippets` directory and run: uv run direct-execution-server or python servers/direct_execution.py"""frommcp.server.fastmcpimportFastMCPmcp=FastMCP("My App") @mcp.tool()defhello(name: str="World") ->str: """Say hello to someone."""returnf"Hello, {name}!"defmain(): """Entry point for the direct execution server."""mcp.run() if__name__=="__main__": main()Full example: examples/snippets/servers/direct_execution.py
Run it with:
python servers/direct_execution.py # or uv run mcp run servers/direct_execution.pyNote that uv run mcp run or uv run mcp dev only supports server using FastMCP and not the low-level server variant.
Note: Streamable HTTP transport is the recommended transport for production deployments. Use
stateless_http=Trueandjson_response=Truefor optimal scalability.
"""Run from the repository root: uv run examples/snippets/servers/streamable_config.py"""frommcp.server.fastmcpimportFastMCP# Stateless server with JSON responses (recommended)mcp=FastMCP("StatelessServer", stateless_http=True, json_response=True) # Other configuration options:# Stateless server with SSE streaming responses# mcp = FastMCP("StatelessServer", stateless_http=True)# Stateful server with session persistence# mcp = FastMCP("StatefulServer")# Add a simple tool to demonstrate the server@mcp.tool()defgreet(name: str="World") ->str: """Greet someone by name."""returnf"Hello, {name}!"# Run server with streamable_http transportif__name__=="__main__": mcp.run(transport="streamable-http")Full example: examples/snippets/servers/streamable_config.py
You can mount multiple FastMCP servers in a Starlette application:
"""Run from the repository root: uvicorn examples.snippets.servers.streamable_starlette_mount:app --reload"""importcontextlibfromstarlette.applicationsimportStarlettefromstarlette.routingimportMountfrommcp.server.fastmcpimportFastMCP# Create the Echo serverecho_mcp=FastMCP(name="EchoServer", stateless_http=True, json_response=True) @echo_mcp.tool()defecho(message: str) ->str: """A simple echo tool"""returnf"Echo: {message}"# Create the Math servermath_mcp=FastMCP(name="MathServer", stateless_http=True, json_response=True) @math_mcp.tool()defadd_two(n: int) ->int: """Tool to add two to the input"""returnn+2# Create a combined lifespan to manage both session managers@contextlib.asynccontextmanagerasyncdeflifespan(app: Starlette): asyncwithcontextlib.AsyncExitStack() asstack: awaitstack.enter_async_context(echo_mcp.session_manager.run()) awaitstack.enter_async_context(math_mcp.session_manager.run()) yield# Create the Starlette app and mount the MCP serversapp=Starlette( routes=[ Mount("/echo", echo_mcp.streamable_http_app()), Mount("/math", math_mcp.streamable_http_app()), ], lifespan=lifespan, ) # Note: Clients connect to http://localhost:8000/echo/mcp and http://localhost:8000/math/mcp# To mount at the root of each path (e.g., /echo instead of /echo/mcp):# echo_mcp.settings.streamable_http_path = "/"# math_mcp.settings.streamable_http_path = "/"Full example: examples/snippets/servers/streamable_starlette_mount.py
For low level server with Streamable HTTP implementations, see:
- Stateful server:
examples/servers/simple-streamablehttp/ - Stateless server:
examples/servers/simple-streamablehttp-stateless/
The streamable HTTP transport supports:
- Stateful and stateless operation modes
- Resumability with event stores
- JSON or SSE response formats
- Better scalability for multi-node deployments
If you'd like your server to be accessible by browser-based MCP clients, you'll need to configure CORS headers. The Mcp-Session-Id header must be exposed for browser clients to access it:
fromstarlette.applicationsimportStarlettefromstarlette.middleware.corsimportCORSMiddleware# Create your Starlette app firststarlette_app=Starlette(routes=[...]) # Then wrap it with CORS middlewarestarlette_app=CORSMiddleware( starlette_app, allow_origins=["*"], # Configure appropriately for productionallow_methods=["GET", "POST", "DELETE"], # MCP streamable HTTP methodsexpose_headers=["Mcp-Session-Id"], )This configuration is necessary because:
- The MCP streamable HTTP transport uses the
Mcp-Session-Idheader for session management - Browsers restrict access to response headers unless explicitly exposed via CORS
- Without this configuration, browser-based clients won't be able to read the session ID from initialization responses
By default, SSE servers are mounted at /sse and Streamable HTTP servers are mounted at /mcp. You can customize these paths using the methods described below.
For more information on mounting applications in Starlette, see the Starlette documentation.
You can mount the StreamableHTTP server to an existing ASGI server using the streamable_http_app method. This allows you to integrate the StreamableHTTP server with other ASGI applications.
"""Basic example showing how to mount StreamableHTTP server in Starlette.Run from the repository root: uvicorn examples.snippets.servers.streamable_http_basic_mounting:app --reload"""importcontextlibfromstarlette.applicationsimportStarlettefromstarlette.routingimportMountfrommcp.server.fastmcpimportFastMCP# Create MCP servermcp=FastMCP("My App", json_response=True) @mcp.tool()defhello() ->str: """A simple hello tool"""return"Hello from MCP!"# Create a lifespan context manager to run the session manager@contextlib.asynccontextmanagerasyncdeflifespan(app: Starlette): asyncwithmcp.session_manager.run(): yield# Mount the StreamableHTTP server to the existing ASGI serverapp=Starlette( routes=[ Mount("/", app=mcp.streamable_http_app()), ], lifespan=lifespan, )Full example: examples/snippets/servers/streamable_http_basic_mounting.py
"""Example showing how to mount StreamableHTTP server using Host-based routing.Run from the repository root: uvicorn examples.snippets.servers.streamable_http_host_mounting:app --reload"""importcontextlibfromstarlette.applicationsimportStarlettefromstarlette.routingimportHostfrommcp.server.fastmcpimportFastMCP# Create MCP servermcp=FastMCP("MCP Host App", json_response=True) @mcp.tool()defdomain_info() ->str: """Get domain-specific information"""return"This is served from mcp.acme.corp"# Create a lifespan context manager to run the session manager@contextlib.asynccontextmanagerasyncdeflifespan(app: Starlette): asyncwithmcp.session_manager.run(): yield# Mount using Host-based routingapp=Starlette( routes=[ Host("mcp.acme.corp", app=mcp.streamable_http_app()), ], lifespan=lifespan, )Full example: examples/snippets/servers/streamable_http_host_mounting.py
"""Example showing how to mount multiple StreamableHTTP servers with path configuration.Run from the repository root: uvicorn examples.snippets.servers.streamable_http_multiple_servers:app --reload"""importcontextlibfromstarlette.applicationsimportStarlettefromstarlette.routingimportMountfrommcp.server.fastmcpimportFastMCP# Create multiple MCP serversapi_mcp=FastMCP("API Server", json_response=True) chat_mcp=FastMCP("Chat Server", json_response=True) @api_mcp.tool()defapi_status() ->str: """Get API status"""return"API is running"@chat_mcp.tool()defsend_message(message: str) ->str: """Send a chat message"""returnf"Message sent: {message}"# Configure servers to mount at the root of each path# This means endpoints will be at /api and /chat instead of /api/mcp and /chat/mcpapi_mcp.settings.streamable_http_path="/"chat_mcp.settings.streamable_http_path="/"# Create a combined lifespan to manage both session managers@contextlib.asynccontextmanagerasyncdeflifespan(app: Starlette): asyncwithcontextlib.AsyncExitStack() asstack: awaitstack.enter_async_context(api_mcp.session_manager.run()) awaitstack.enter_async_context(chat_mcp.session_manager.run()) yield# Mount the serversapp=Starlette( routes=[ Mount("/api", app=api_mcp.streamable_http_app()), Mount("/chat", app=chat_mcp.streamable_http_app()), ], lifespan=lifespan, )Full example: examples/snippets/servers/streamable_http_multiple_servers.py
"""Example showing path configuration during FastMCP initialization.Run from the repository root: uvicorn examples.snippets.servers.streamable_http_path_config:app --reload"""fromstarlette.applicationsimportStarlettefromstarlette.routingimportMountfrommcp.server.fastmcpimportFastMCP# Configure streamable_http_path during initialization# This server will mount at the root of wherever it's mountedmcp_at_root=FastMCP( "My Server", json_response=True, streamable_http_path="/", ) @mcp_at_root.tool()defprocess_data(data: str) ->str: """Process some data"""returnf"Processed: {data}"# Mount at /process - endpoints will be at /process instead of /process/mcpapp=Starlette( routes=[ Mount("/process", app=mcp_at_root.streamable_http_app()), ] )Full example: examples/snippets/servers/streamable_http_path_config.py
Note: SSE transport is being superseded by Streamable HTTP transport.
You can mount the SSE server to an existing ASGI server using the sse_app method. This allows you to integrate the SSE server with other ASGI applications.
fromstarlette.applicationsimportStarlettefromstarlette.routingimportMount, Hostfrommcp.server.fastmcpimportFastMCPmcp=FastMCP("My App") # Mount the SSE server to the existing ASGI serverapp=Starlette( routes=[ Mount('/', app=mcp.sse_app()), ] ) # or dynamically mount as hostapp.router.routes.append(Host('mcp.acme.corp', app=mcp.sse_app()))When mounting multiple MCP servers under different paths, you can configure the mount path in several ways:
fromstarlette.applicationsimportStarlettefromstarlette.routingimportMountfrommcp.server.fastmcpimportFastMCP# Create multiple MCP serversgithub_mcp=FastMCP("GitHub API") browser_mcp=FastMCP("Browser") curl_mcp=FastMCP("Curl") search_mcp=FastMCP("Search") # Method 1: Configure mount paths via settings (recommended for persistent configuration)github_mcp.settings.mount_path="/github"browser_mcp.settings.mount_path="/browser"# Method 2: Pass mount path directly to sse_app (preferred for ad-hoc mounting)# This approach doesn't modify the server's settings permanently# Create Starlette app with multiple mounted serversapp=Starlette( routes=[ # Using settings-based configurationMount("/github", app=github_mcp.sse_app()), Mount("/browser", app=browser_mcp.sse_app()), # Using direct mount path parameterMount("/curl", app=curl_mcp.sse_app("/curl")), Mount("/search", app=search_mcp.sse_app("/search")), ] ) # Method 3: For direct execution, you can also pass the mount path to run()if__name__=="__main__": search_mcp.run(transport="sse", mount_path="/search")For more information on mounting applications in Starlette, see the Starlette documentation.
For more control, you can use the low-level server implementation directly. This gives you full access to the protocol and allows you to customize every aspect of your server, including lifecycle management through the lifespan API:
"""Run from the repository root: uv run examples/snippets/servers/lowlevel/lifespan.py"""fromcollections.abcimportAsyncIteratorfromcontextlibimportasynccontextmanagerfromtypingimportAnyimportmcp.server.stdioimportmcp.typesastypesfrommcp.server.lowlevelimportNotificationOptions, Serverfrommcp.server.modelsimportInitializationOptions# Mock database class for exampleclassDatabase: """Mock database class for example."""@classmethodasyncdefconnect(cls) ->"Database": """Connect to database."""print("Database connected") returncls() asyncdefdisconnect(self) ->None: """Disconnect from database."""print("Database disconnected") asyncdefquery(self, query_str: str) ->list[dict[str, str]]: """Execute a query."""# Simulate database queryreturn [{"id": "1", "name": "Example", "query": query_str}] @asynccontextmanagerasyncdefserver_lifespan(_server: Server) ->AsyncIterator[dict[str, Any]]: """Manage server startup and shutdown lifecycle."""# Initialize resources on startupdb=awaitDatabase.connect() try: yield{"db": db} finally: # Clean up on shutdownawaitdb.disconnect() # Pass lifespan to serverserver=Server("example-server", lifespan=server_lifespan) @server.list_tools()asyncdefhandle_list_tools() ->list[types.Tool]: """List available tools."""return [ types.Tool( name="query_db", description="Query the database", inputSchema={"type": "object", "properties":{"query":{"type": "string", "description": "SQL query to execute"}}, "required": ["query"], }, ) ] @server.call_tool()asyncdefquery_db(name: str, arguments: dict[str, Any]) ->list[types.TextContent]: """Handle database query tool call."""ifname!="query_db": raiseValueError(f"Unknown tool: {name}") # Access lifespan contextctx=server.request_contextdb=ctx.lifespan_context["db"] # Execute queryresults=awaitdb.query(arguments["query"]) return [types.TextContent(type="text", text=f"Query results: {results}")] asyncdefrun(): """Run the server with lifespan management."""asyncwithmcp.server.stdio.stdio_server() as (read_stream, write_stream): awaitserver.run( read_stream, write_stream, InitializationOptions( server_name="example-server", server_version="0.1.0", capabilities=server.get_capabilities( notification_options=NotificationOptions(), experimental_capabilities={}, ), ), ) if__name__=="__main__": importasyncioasyncio.run(run())Full example: examples/snippets/servers/lowlevel/lifespan.py
The lifespan API provides:
- A way to initialize resources when the server starts and clean them up when it stops
- Access to initialized resources through the request context in handlers
- Type-safe context passing between lifespan and request handlers
"""Run from the repository root:uv run examples/snippets/servers/lowlevel/basic.py"""importasyncioimportmcp.server.stdioimportmcp.typesastypesfrommcp.server.lowlevelimportNotificationOptions, Serverfrommcp.server.modelsimportInitializationOptions# Create a server instanceserver=Server("example-server") @server.list_prompts()asyncdefhandle_list_prompts() ->list[types.Prompt]: """List available prompts."""return [ types.Prompt( name="example-prompt", description="An example prompt template", arguments=[types.PromptArgument(name="arg1", description="Example argument", required=True)], ) ] @server.get_prompt()asyncdefhandle_get_prompt(name: str, arguments: dict[str, str] |None) ->types.GetPromptResult: """Get a specific prompt by name."""ifname!="example-prompt": raiseValueError(f"Unknown prompt: {name}") arg1_value= (argumentsor{}).get("arg1", "default") returntypes.GetPromptResult( description="Example prompt", messages=[ types.PromptMessage( role="user", content=types.TextContent(type="text", text=f"Example prompt text with argument: {arg1_value}"), ) ], ) asyncdefrun(): """Run the basic low-level server."""asyncwithmcp.server.stdio.stdio_server() as (read_stream, write_stream): awaitserver.run( read_stream, write_stream, InitializationOptions( server_name="example", server_version="0.1.0", capabilities=server.get_capabilities( notification_options=NotificationOptions(), experimental_capabilities={}, ), ), ) if__name__=="__main__": asyncio.run(run())Full example: examples/snippets/servers/lowlevel/basic.py
Caution: The uv run mcp run and uv run mcp dev tool doesn't support low-level server.
The low-level server supports structured output for tools, allowing you to return both human-readable content and machine-readable structured data. Tools can define an outputSchema to validate their structured output:
"""Run from the repository root: uv run examples/snippets/servers/lowlevel/structured_output.py"""importasynciofromtypingimportAnyimportmcp.server.stdioimportmcp.typesastypesfrommcp.server.lowlevelimportNotificationOptions, Serverfrommcp.server.modelsimportInitializationOptionsserver=Server("example-server") @server.list_tools()asyncdeflist_tools() ->list[types.Tool]: """List available tools with structured output schemas."""return [ types.Tool( name="get_weather", description="Get current weather for a city", inputSchema={"type": "object", "properties":{"city":{"type": "string", "description": "City name"}}, "required": ["city"], }, outputSchema={"type": "object", "properties":{"temperature":{"type": "number", "description": "Temperature in Celsius"}, "condition":{"type": "string", "description": "Weather condition"}, "humidity":{"type": "number", "description": "Humidity percentage"}, "city":{"type": "string", "description": "City name"}, }, "required": ["temperature", "condition", "humidity", "city"], }, ) ] @server.call_tool()asyncdefcall_tool(name: str, arguments: dict[str, Any]) ->dict[str, Any]: """Handle tool calls with structured output."""ifname=="get_weather": city=arguments["city"] # Simulated weather data - in production, call a weather APIweather_data={"temperature": 22.5, "condition": "partly cloudy", "humidity": 65, "city": city, # Include the requested city } # low-level server will validate structured output against the tool's# output schema, and additionally serialize it into a TextContent block# for backwards compatibility with pre-2025-06-18 clients.returnweather_dataelse: raiseValueError(f"Unknown tool: {name}") asyncdefrun(): """Run the structured output server."""asyncwithmcp.server.stdio.stdio_server() as (read_stream, write_stream): awaitserver.run( read_stream, write_stream, InitializationOptions( server_name="structured-output-example", server_version="0.1.0", capabilities=server.get_capabilities( notification_options=NotificationOptions(), experimental_capabilities={}, ), ), ) if__name__=="__main__": asyncio.run(run())Full example: examples/snippets/servers/lowlevel/structured_output.py
Tools can return data in four ways:
- Content only: Return a list of content blocks (default behavior before spec revision 2025-06-18)
- Structured data only: Return a dictionary that will be serialized to JSON (Introduced in spec revision 2025-06-18)
- Both: Return a tuple of (content, structured_data) preferred option to use for backwards compatibility
- Direct CallToolResult: Return
CallToolResultdirectly for full control (including_metafield)
When an outputSchema is defined, the server automatically validates the structured output against the schema. This ensures type safety and helps catch errors early.
For full control over the response including the _meta field (for passing data to client applications without exposing it to the model), return CallToolResult directly:
"""Run from the repository root: uv run examples/snippets/servers/lowlevel/direct_call_tool_result.py"""importasynciofromtypingimportAnyimportmcp.server.stdioimportmcp.typesastypesfrommcp.server.lowlevelimportNotificationOptions, Serverfrommcp.server.modelsimportInitializationOptionsserver=Server("example-server") @server.list_tools()asyncdeflist_tools() ->list[types.Tool]: """List available tools."""return [ types.Tool( name="advanced_tool", description="Tool with full control including _meta field", inputSchema={"type": "object", "properties":{"message":{"type": "string"}}, "required": ["message"], }, ) ] @server.call_tool()asyncdefhandle_call_tool(name: str, arguments: dict[str, Any]) ->types.CallToolResult: """Handle tool calls by returning CallToolResult directly."""ifname=="advanced_tool": message=str(arguments.get("message", "")) returntypes.CallToolResult( content=[types.TextContent(type="text", text=f"Processed: {message}")], structuredContent={"result": "success", "message": message}, _meta={"hidden": "data for client applications only"}, ) raiseValueError(f"Unknown tool: {name}") asyncdefrun(): """Run the server."""asyncwithmcp.server.stdio.stdio_server() as (read_stream, write_stream): awaitserver.run( read_stream, write_stream, InitializationOptions( server_name="example", server_version="0.1.0", capabilities=server.get_capabilities( notification_options=NotificationOptions(), experimental_capabilities={}, ), ), ) if__name__=="__main__": asyncio.run(run())Full example: examples/snippets/servers/lowlevel/direct_call_tool_result.py
Note: When returning CallToolResult, you bypass the automatic content/structured conversion. You must construct the complete response yourself.
For servers that need to handle large datasets, the low-level server provides paginated versions of list operations. This is an optional optimization - most servers won't need pagination unless they're dealing with hundreds or thousands of items.
"""Example of implementing pagination with MCP server decorators."""frompydanticimportAnyUrlimportmcp.typesastypesfrommcp.server.lowlevelimportServer# Initialize the serverserver=Server("paginated-server") # Sample data to paginateITEMS= [f"Item {i}"foriinrange(1, 101)] # 100 items@server.list_resources()asyncdeflist_resources_paginated(request: types.ListResourcesRequest) ->types.ListResourcesResult: """List resources with pagination support."""page_size=10# Extract cursor from request paramscursor=request.params.cursorifrequest.paramsisnotNoneelseNone# Parse cursor to get offsetstart=0ifcursorisNoneelseint(cursor) end=start+page_size# Get page of resourcespage_items= [ types.Resource(uri=AnyUrl(f"resource://items/{item}"), name=item, description=f"Description for {item}") foriteminITEMS[start:end] ] # Determine next cursornext_cursor=str(end) ifend<len(ITEMS) elseNonereturntypes.ListResourcesResult(resources=page_items, nextCursor=next_cursor)Full example: examples/snippets/servers/pagination_example.py
"""Example of consuming paginated MCP endpoints from a client."""importasynciofrommcp.client.sessionimportClientSessionfrommcp.client.stdioimportStdioServerParameters, stdio_clientfrommcp.typesimportPaginatedRequestParams, Resourceasyncdeflist_all_resources() ->None: """Fetch all resources using pagination."""asyncwithstdio_client(StdioServerParameters(command="uv", args=["run", "mcp-simple-pagination"])) as ( read, write, ): asyncwithClientSession(read, write) assession: awaitsession.initialize() all_resources: list[Resource] = [] cursor=NonewhileTrue: # Fetch a page of resourcesresult=awaitsession.list_resources(params=PaginatedRequestParams(cursor=cursor)) all_resources.extend(result.resources) print(f"Fetched {len(result.resources)} resources") # Check if there are more pagesifresult.nextCursor: cursor=result.nextCursorelse: breakprint(f"Total resources: {len(all_resources)}") if__name__=="__main__": asyncio.run(list_all_resources())Full example: examples/snippets/clients/pagination_client.py
- Cursors are opaque strings - the server defines the format (numeric offsets, timestamps, etc.)
- Return
nextCursor=Nonewhen there are no more pages - Backward compatible - clients that don't support pagination will still work (they'll just get the first page)
- Flexible page sizes - Each endpoint can define its own page size based on data characteristics
See the simple-pagination example for a complete implementation.
The SDK provides a high-level client interface for connecting to MCP servers using various transports:
"""cd to the `examples/snippets/clients` directory and run: uv run client"""importasyncioimportosfrompydanticimportAnyUrlfrommcpimportClientSession, StdioServerParameters, typesfrommcp.client.stdioimportstdio_clientfrommcp.shared.contextimportRequestContext# Create server parameters for stdio connectionserver_params=StdioServerParameters( command="uv", # Using uv to run the serverargs=["run", "server", "fastmcp_quickstart", "stdio"], # We're already in snippets direnv={"UV_INDEX": os.environ.get("UV_INDEX", "")}, ) # Optional: create a sampling callbackasyncdefhandle_sampling_message( context: RequestContext[ClientSession, None], params: types.CreateMessageRequestParams ) ->types.CreateMessageResult: print(f"Sampling request: {params.messages}") returntypes.CreateMessageResult( role="assistant", content=types.TextContent( type="text", text="Hello, world! from model", ), model="gpt-3.5-turbo", stopReason="endTurn", ) asyncdefrun(): asyncwithstdio_client(server_params) as (read, write): asyncwithClientSession(read, write, sampling_callback=handle_sampling_message) assession: # Initialize the connectionawaitsession.initialize() # List available promptsprompts=awaitsession.list_prompts() print(f"Available prompts: {[p.nameforpinprompts.prompts]}") # Get a prompt (greet_user prompt from fastmcp_quickstart)ifprompts.prompts: prompt=awaitsession.get_prompt("greet_user", arguments={"name": "Alice", "style": "friendly"}) print(f"Prompt result: {prompt.messages[0].content}") # List available resourcesresources=awaitsession.list_resources() print(f"Available resources: {[r.uriforrinresources.resources]}") # List available toolstools=awaitsession.list_tools() print(f"Available tools: {[t.namefortintools.tools]}") # Read a resource (greeting resource from fastmcp_quickstart)resource_content=awaitsession.read_resource(AnyUrl("greeting://World")) content_block=resource_content.contents[0] ifisinstance(content_block, types.TextContent): print(f"Resource content: {content_block.text}") # Call a tool (add tool from fastmcp_quickstart)result=awaitsession.call_tool("add", arguments={"a": 5, "b": 3}) result_unstructured=result.content[0] ifisinstance(result_unstructured, types.TextContent): print(f"Tool result: {result_unstructured.text}") result_structured=result.structuredContentprint(f"Structured tool result: {result_structured}") defmain(): """Entry point for the client script."""asyncio.run(run()) if__name__=="__main__": main()Full example: examples/snippets/clients/stdio_client.py
Clients can also connect using Streamable HTTP transport:
"""Run from the repository root: uv run examples/snippets/clients/streamable_basic.py"""importasynciofrommcpimportClientSessionfrommcp.client.streamable_httpimportstreamable_http_clientasyncdefmain(): # Connect to a streamable HTTP serverasyncwithstreamable_http_client("http://localhost:8000/mcp") as ( read_stream, write_stream, _, ): # Create a session using the client streamsasyncwithClientSession(read_stream, write_stream) assession: # Initialize the connectionawaitsession.initialize() # List available toolstools=awaitsession.list_tools() print(f"Available tools: {[tool.namefortoolintools.tools]}") if__name__=="__main__": asyncio.run(main())Full example: examples/snippets/clients/streamable_basic.py
When building MCP clients, the SDK provides utilities to help display human-readable names for tools, resources, and prompts:
"""cd to the `examples/snippets` directory and run: uv run display-utilities-client"""importasyncioimportosfrommcpimportClientSession, StdioServerParametersfrommcp.client.stdioimportstdio_clientfrommcp.shared.metadata_utilsimportget_display_name# Create server parameters for stdio connectionserver_params=StdioServerParameters( command="uv", # Using uv to run the serverargs=["run", "server", "fastmcp_quickstart", "stdio"], env={"UV_INDEX": os.environ.get("UV_INDEX", "")}, ) asyncdefdisplay_tools(session: ClientSession): """Display available tools with human-readable names"""tools_response=awaitsession.list_tools() fortoolintools_response.tools: # get_display_name() returns the title if available, otherwise the namedisplay_name=get_display_name(tool) print(f"Tool: {display_name}") iftool.description: print(f" {tool.description}") asyncdefdisplay_resources(session: ClientSession): """Display available resources with human-readable names"""resources_response=awaitsession.list_resources() forresourceinresources_response.resources: display_name=get_display_name(resource) print(f"Resource: {display_name} ({resource.uri})") templates_response=awaitsession.list_resource_templates() fortemplateintemplates_response.resourceTemplates: display_name=get_display_name(template) print(f"Resource Template: {display_name}") asyncdefrun(): """Run the display utilities example."""asyncwithstdio_client(server_params) as (read, write): asyncwithClientSession(read, write) assession: # Initialize the connectionawaitsession.initialize() print("=== Available Tools ===") awaitdisplay_tools(session) print("\n=== Available Resources ===") awaitdisplay_resources(session) defmain(): """Entry point for the display utilities client."""asyncio.run(run()) if__name__=="__main__": main()Full example: examples/snippets/clients/display_utilities.py
The get_display_name() function implements the proper precedence rules for displaying names:
- For tools:
title>annotations.title>name - For other objects:
title>name
This ensures your client UI shows the most user-friendly names that servers provide.
The SDK includes authorization support for connecting to protected MCP servers:
"""Before running, specify running MCP RS server URL.To spin up RS server locally, see examples/servers/simple-auth/README.mdcd to the `examples/snippets` directory and run: uv run oauth-client"""importasynciofromurllib.parseimportparse_qs, urlparseimporthttpxfrompydanticimportAnyUrlfrommcpimportClientSessionfrommcp.client.authimportOAuthClientProvider, TokenStoragefrommcp.client.streamable_httpimportstreamable_http_clientfrommcp.shared.authimportOAuthClientInformationFull, OAuthClientMetadata, OAuthTokenclassInMemoryTokenStorage(TokenStorage): """Demo In-memory token storage implementation."""def__init__(self): self.tokens: OAuthToken|None=Noneself.client_info: OAuthClientInformationFull|None=Noneasyncdefget_tokens(self) ->OAuthToken|None: """Get stored tokens."""returnself.tokensasyncdefset_tokens(self, tokens: OAuthToken) ->None: """Store tokens."""self.tokens=tokensasyncdefget_client_info(self) ->OAuthClientInformationFull|None: """Get stored client information."""returnself.client_infoasyncdefset_client_info(self, client_info: OAuthClientInformationFull) ->None: """Store client information."""self.client_info=client_infoasyncdefhandle_redirect(auth_url: str) ->None: print(f"Visit: {auth_url}") asyncdefhandle_callback() ->tuple[str, str|None]: callback_url=input("Paste callback URL: ") params=parse_qs(urlparse(callback_url).query) returnparams["code"][0], params.get("state", [None])[0] asyncdefmain(): """Run the OAuth client example."""oauth_auth=OAuthClientProvider( server_url="http://localhost:8001", client_metadata=OAuthClientMetadata( client_name="Example MCP Client", redirect_uris=[AnyUrl("http://localhost:3000/callback")], grant_types=["authorization_code", "refresh_token"], response_types=["code"], scope="user", ), storage=InMemoryTokenStorage(), redirect_handler=handle_redirect, callback_handler=handle_callback, ) asyncwithhttpx.AsyncClient(auth=oauth_auth, follow_redirects=True) ascustom_client: asyncwithstreamable_http_client("http://localhost:8001/mcp", http_client=custom_client) as (read, write, _): asyncwithClientSession(read, write) assession: awaitsession.initialize() tools=awaitsession.list_tools() print(f"Available tools: {[tool.namefortoolintools.tools]}") resources=awaitsession.list_resources() print(f"Available resources: {[r.uriforrinresources.resources]}") defrun(): asyncio.run(main()) if__name__=="__main__": run()Full example: examples/snippets/clients/oauth_client.py
For a complete working example, see examples/clients/simple-auth-client/.
When calling tools through MCP, the CallToolResult object contains the tool's response in a structured format. Understanding how to parse this result is essential for properly handling tool outputs.
"""examples/snippets/clients/parsing_tool_results.py"""importasynciofrommcpimportClientSession, StdioServerParameters, typesfrommcp.client.stdioimportstdio_clientasyncdefparse_tool_results(): """Demonstrates how to parse different types of content in CallToolResult."""server_params=StdioServerParameters( command="python", args=["path/to/mcp_server.py"] ) asyncwithstdio_client(server_params) as (read, write): asyncwithClientSession(read, write) assession: awaitsession.initialize() # Example 1: Parsing text contentresult=awaitsession.call_tool("get_data",{"format": "text"}) forcontentinresult.content: ifisinstance(content, types.TextContent): print(f"Text: {content.text}") # Example 2: Parsing structured content from JSON toolsresult=awaitsession.call_tool("get_user",{"id": "123"}) ifhasattr(result, "structuredContent") andresult.structuredContent: # Access structured data directlyuser_data=result.structuredContentprint(f"User: {user_data.get('name')}, Age: {user_data.get('age')}") # Example 3: Parsing embedded resourcesresult=awaitsession.call_tool("read_config",{}) forcontentinresult.content: ifisinstance(content, types.EmbeddedResource): resource=content.resourceifisinstance(resource, types.TextResourceContents): print(f"Config from {resource.uri}: {resource.text}") elifisinstance(resource, types.BlobResourceContents): print(f"Binary data from {resource.uri}") # Example 4: Parsing image contentresult=awaitsession.call_tool("generate_chart",{"data": [1, 2, 3]}) forcontentinresult.content: ifisinstance(content, types.ImageContent): print(f"Image ({content.mimeType}): {len(content.data)} bytes") # Example 5: Handling errorsresult=awaitsession.call_tool("failing_tool",{}) ifresult.isError: print("Tool execution failed!") forcontentinresult.content: ifisinstance(content, types.TextContent): print(f"Error: {content.text}") asyncdefmain(): awaitparse_tool_results() if__name__=="__main__": asyncio.run(main())The MCP protocol defines three core primitives that servers can implement:
| Primitive | Control | Description | Example Use |
|---|---|---|---|
| Prompts | User-controlled | Interactive templates invoked by user choice | Slash commands, menu options |
| Resources | Application-controlled | Contextual data managed by the client application | File contents, API responses |
| Tools | Model-controlled | Functions exposed to the LLM to take actions | API calls, data updates |
MCP servers declare capabilities during initialization:
| Capability | Feature Flag | Description |
|---|---|---|
prompts | listChanged | Prompt template management |
resources | subscribelistChanged | Resource exposure and updates |
tools | listChanged | Tool discovery and execution |
logging | - | Server logging configuration |
completions | - | Argument completion suggestions |
- API Reference
- Experimental Features (Tasks)
- Model Context Protocol documentation
- Model Context Protocol specification
- Officially supported servers
We are passionate about supporting contributors of all levels of experience and would love to see you get involved in the project. See the contributing guide to get started.
This project is licensed under the MIT License - see the LICENSE file for details.