> ## Documentation Index > Fetch the complete documentation index at: https://fastmcp-docs-v3-beta2-feature-tracking.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # context # `fastmcp.server.context` ## Functions ### `set_transport` ```python theme={null} set_transport(transport: TransportType) -> Token[TransportType | None] ``` Set the current transport type. Returns token for reset. ### `reset_transport` ```python theme={null} reset_transport(token: Token[TransportType | None]) -> None ``` Reset transport to previous value. ### `set_context` ```python theme={null} set_context(context: Context) -> Generator[Context, None, None] ``` ## Classes ### `LogData` Data object for passing log arguments to client-side handlers. This provides an interface to match the Python standard library logging, for compatibility with structured logging. ### `Context` Context object providing access to MCP capabilities. This provides a cleaner interface to MCP's RequestContext functionality. It gets injected into tool and resource functions that request it via type hints. To use context in a tool function, add a parameter with the Context type annotation: ```python theme={null} @server.tool async def my_tool(x: int, ctx: Context) -> str: # Log messages to the client await ctx.info(f"Processing {x}") await ctx.debug("Debug info") await ctx.warning("Warning message") await ctx.error("Error message") # Report progress await ctx.report_progress(50, 100, "Processing") # Access resources data = await ctx.read_resource("resource://data") # Get request info request_id = ctx.request_id client_id = ctx.client_id # Manage state across the session (persists across requests) await ctx.set_state("key", "value") value = await ctx.get_state("key") return str(x) ``` State Management: Context provides session-scoped state that persists across requests within the same MCP session. State is automatically keyed by session, ensuring isolation between different clients. State set during `on_initialize` middleware will persist to subsequent tool calls when using the same session object (STDIO, SSE, single-server HTTP). For distributed/serverless HTTP deployments where different machines handle the init and tool calls, state is isolated by the mcp-session-id header. The context parameter name can be anything as long as it's annotated with Context. The context is optional - tools that don't need it can omit the parameter. **Methods:** #### `is_background_task` ```python theme={null} is_background_task(self) -> bool ``` True when this context is running in a background task (Docket worker). When True, certain operations like elicit() and sample() will use task-aware implementations that can pause the task and wait for client input. #### `task_id` ```python theme={null} task_id(self) -> str | None ``` Get the background task ID if running in a background task. Returns None if not running in a background task context. #### `fastmcp` ```python theme={null} fastmcp(self) -> FastMCP ``` Get the FastMCP instance. #### `request_context` ```python theme={null} request_context(self) -> RequestContext[ServerSession, Any, Request] | None ``` Access to the underlying request context. Returns None when the MCP session has not been established yet. Returns the full RequestContext once the MCP session is available. For HTTP request access in middleware, use `get_http_request()` from fastmcp.server.dependencies, which works whether or not the MCP session is available. Example in middleware: ```python theme={null} async def on_request(self, context, call_next): ctx = context.fastmcp_context if ctx.request_context: # MCP session available - can access session_id, request_id, etc. session_id = ctx.session_id else: # MCP session not available yet - use HTTP helpers from fastmcp.server.dependencies import get_http_request request = get_http_request() return await call_next(context) ``` #### `lifespan_context` ```python theme={null} lifespan_context(self) -> dict[str, Any] ``` Access the server's lifespan context. Returns the context dict yielded by the server's lifespan function. Returns an empty dict if no lifespan was configured or if the MCP session is not yet established. Example: ```python theme={null} @server.tool def my_tool(ctx: Context) -> str: db = ctx.lifespan_context.get("db") if db: return db.query("SELECT 1") return "No database connection" ``` #### `report_progress` ```python theme={null} report_progress(self, progress: float, total: float | None = None, message: str | None = None) -> None ``` Report progress for the current operation. **Args:** * `progress`: Current progress value e.g. 24 * `total`: Optional total value e.g. 100 #### `list_resources` ```python theme={null} list_resources(self) -> list[SDKResource] ``` List all available resources from the server. **Returns:** * List of Resource objects available on the server #### `list_prompts` ```python theme={null} list_prompts(self) -> list[SDKPrompt] ``` List all available prompts from the server. **Returns:** * List of Prompt objects available on the server #### `get_prompt` ```python theme={null} get_prompt(self, name: str, arguments: dict[str, Any] | None = None) -> GetPromptResult ``` Get a prompt by name with optional arguments. **Args:** * `name`: The name of the prompt to get * `arguments`: Optional arguments to pass to the prompt **Returns:** * The prompt result #### `read_resource` ```python theme={null} read_resource(self, uri: str | AnyUrl) -> ResourceResult ``` Read a resource by URI. **Args:** * `uri`: Resource URI to read **Returns:** * ResourceResult with contents #### `log` ```python theme={null} log(self, message: str, level: LoggingLevel | None = None, logger_name: str | None = None, extra: Mapping[str, Any] | None = None) -> None ``` Send a log message to the client. Messages sent to Clients are also logged to the `fastmcp.server.context.to_client` logger with a level of `DEBUG`. **Args:** * `message`: Log message * `level`: Optional log level. One of "debug", "info", "notice", "warning", "error", "critical", "alert", or "emergency". Default is "info". * `logger_name`: Optional logger name * `extra`: Optional mapping for additional arguments #### `transport` ```python theme={null} transport(self) -> TransportType | None ``` Get the current transport type. Returns the transport type used to run this server: "stdio", "sse", or "streamable-http". Returns None if called outside of a server context. #### `client_supports_extension` ```python theme={null} client_supports_extension(self, extension_id: str) -> bool ``` Check whether the connected client supports a given MCP extension. Inspects the `extensions` extra field on `ClientCapabilities` sent by the client during initialization. Returns `False` when no session is available (e.g., outside a request context) or when the client did not advertise the extension. Example:: from fastmcp.server.apps import UI\_EXTENSION\_ID @mcp.tool async def my\_tool(ctx: Context) -> str: if ctx.client\_supports\_extension(UI\_EXTENSION\_ID): return "UI-capable client" return "text-only client" #### `client_id` ```python theme={null} client_id(self) -> str | None ``` Get the client ID if available. #### `request_id` ```python theme={null} request_id(self) -> str ``` Get the unique ID for this request. Raises RuntimeError if MCP request context is not available. #### `session_id` ```python theme={null} session_id(self) -> str ``` Get the MCP session ID for ALL transports. Returns the session ID that can be used as a key for session-based data storage (e.g., Redis) to share data between tool calls within the same client session. **Returns:** * The session ID for StreamableHTTP transports, or a generated ID * for other transports. #### `session` ```python theme={null} session(self) -> ServerSession ``` Access to the underlying session for advanced usage. In request mode: Returns the session from the active request context. In background task mode: Returns the session stored at Context creation. Raises RuntimeError if no session is available. #### `debug` ```python theme={null} debug(self, message: str, logger_name: str | None = None, extra: Mapping[str, Any] | None = None) -> None ``` Send a `DEBUG`-level message to the connected MCP Client. Messages sent to Clients are also logged to the `fastmcp.server.context.to_client` logger with a level of `DEBUG`. #### `info` ```python theme={null} info(self, message: str, logger_name: str | None = None, extra: Mapping[str, Any] | None = None) -> None ``` Send a `INFO`-level message to the connected MCP Client. Messages sent to Clients are also logged to the `fastmcp.server.context.to_client` logger with a level of `DEBUG`. #### `warning` ```python theme={null} warning(self, message: str, logger_name: str | None = None, extra: Mapping[str, Any] | None = None) -> None ``` Send a `WARNING`-level message to the connected MCP Client. Messages sent to Clients are also logged to the `fastmcp.server.context.to_client` logger with a level of `DEBUG`. #### `error` ```python theme={null} error(self, message: str, logger_name: str | None = None, extra: Mapping[str, Any] | None = None) -> None ``` Send a `ERROR`-level message to the connected MCP Client. Messages sent to Clients are also logged to the `fastmcp.server.context.to_client` logger with a level of `DEBUG`. #### `list_roots` ```python theme={null} list_roots(self) -> list[Root] ``` List the roots available to the server, as indicated by the client. #### `send_notification` ```python theme={null} send_notification(self, notification: mcp.types.ServerNotificationType) -> None ``` Send a notification to the client immediately. **Args:** * `notification`: An MCP notification instance (e.g., ToolListChangedNotification()) #### `close_sse_stream` ```python theme={null} close_sse_stream(self) -> None ``` Close the current response stream to trigger client reconnection. When using StreamableHTTP transport with an EventStore configured, this method gracefully closes the HTTP connection for the current request. The client will automatically reconnect (after `retry_interval` milliseconds) and resume receiving events from where it left off via the EventStore. This is useful for long-running operations to avoid load balancer timeouts. Instead of holding a connection open for minutes, you can periodically close and let the client reconnect. #### `sample_step` ```python theme={null} sample_step(self, messages: str | Sequence[str | SamplingMessage]) -> SampleStep ``` Make a single LLM sampling call. This is a stateless function that makes exactly one LLM call and optionally executes any requested tools. Use this for fine-grained control over the sampling loop. **Args:** * `messages`: The message(s) to send. Can be a string, list of strings, or list of SamplingMessage objects. * `system_prompt`: Optional system prompt for the LLM. * `temperature`: Optional sampling temperature. * `max_tokens`: Maximum tokens to generate. Defaults to 512. * `model_preferences`: Optional model preferences. * `tools`: Optional list of tools the LLM can use. * `tool_choice`: Tool choice mode ("auto", "required", or "none"). * `execute_tools`: If True (default), execute tool calls and append results to history. If False, return immediately with tool\_calls available in the step for manual execution. * `mask_error_details`: If True, mask detailed error messages from tool execution. When None (default), uses the global settings value. Tools can raise ToolError to bypass masking. **Returns:** * SampleStep containing: * * .response: The raw LLM response * * .history: Messages including input, assistant response, and tool results * * .is\_tool\_use: True if the LLM requested tool execution * * .tool\_calls: List of tool calls (if any) * * .text: The text content (if any) #### `sample` ```python theme={null} sample(self, messages: str | Sequence[str | SamplingMessage]) -> SamplingResult[ResultT] ``` Overload: With result\_type, returns SamplingResult\[ResultT]. #### `sample` ```python theme={null} sample(self, messages: str | Sequence[str | SamplingMessage]) -> SamplingResult[str] ``` Overload: Without result\_type, returns SamplingResult\[str]. #### `sample` ```python theme={null} sample(self, messages: str | Sequence[str | SamplingMessage]) -> SamplingResult[ResultT] | SamplingResult[str] ``` Send a sampling request to the client and await the response. This method runs to completion automatically. When tools are provided, it executes a tool loop: if the LLM returns a tool use request, the tools are executed and the results are sent back to the LLM. This continues until the LLM provides a final text response. When result\_type is specified, a synthetic `final_response` tool is created. The LLM calls this tool to provide the structured response, which is validated against the result\_type and returned as `.result`. For fine-grained control over the sampling loop, use sample\_step() instead. **Args:** * `messages`: The message(s) to send. Can be a string, list of strings, or list of SamplingMessage objects. * `system_prompt`: Optional system prompt for the LLM. * `temperature`: Optional sampling temperature. * `max_tokens`: Maximum tokens to generate. Defaults to 512. * `model_preferences`: Optional model preferences. * `tools`: Optional list of tools the LLM can use. Accepts plain functions or SamplingTools. * `result_type`: Optional type for structured output. When specified, a synthetic `final_response` tool is created and the LLM's response is validated against this type. * `mask_error_details`: If True, mask detailed error messages from tool execution. When None (default), uses the global settings value. Tools can raise ToolError to bypass masking. **Returns:** * SamplingResult\[T] containing: * * .text: The text representation (raw text or JSON for structured) * * .result: The typed result (str for text, parsed object for structured) * * .history: All messages exchanged during sampling #### `elicit` ```python theme={null} elicit(self, message: str, response_type: None) -> AcceptedElicitation[dict[str, Any]] | DeclinedElicitation | CancelledElicitation ``` #### `elicit` ```python theme={null} elicit(self, message: str, response_type: type[T]) -> AcceptedElicitation[T] | DeclinedElicitation | CancelledElicitation ``` #### `elicit` ```python theme={null} elicit(self, message: str, response_type: list[str]) -> AcceptedElicitation[str] | DeclinedElicitation | CancelledElicitation ``` #### `elicit` ```python theme={null} elicit(self, message: str, response_type: dict[str, dict[str, str]]) -> AcceptedElicitation[str] | DeclinedElicitation | CancelledElicitation ``` #### `elicit` ```python theme={null} elicit(self, message: str, response_type: list[list[str]]) -> AcceptedElicitation[list[str]] | DeclinedElicitation | CancelledElicitation ``` #### `elicit` ```python theme={null} elicit(self, message: str, response_type: list[dict[str, dict[str, str]]]) -> AcceptedElicitation[list[str]] | DeclinedElicitation | CancelledElicitation ``` #### `elicit` ```python theme={null} elicit(self, message: str, response_type: type[T] | list[str] | dict[str, dict[str, str]] | list[list[str]] | list[dict[str, dict[str, str]]] | None = None) -> AcceptedElicitation[T] | AcceptedElicitation[dict[str, Any]] | AcceptedElicitation[str] | AcceptedElicitation[list[str]] | DeclinedElicitation | CancelledElicitation ``` Send an elicitation request to the client and await the response. Call this method at any time to request additional information from the user through the client. The client must support elicitation, or the request will error. Note that the MCP protocol only supports simple object schemas with primitive types. You can provide a dataclass, TypedDict, or BaseModel to comply. If you provide a primitive type, an object schema with a single "value" field will be generated for the MCP interaction and automatically deconstructed into the primitive type upon response. If the response\_type is None, the generated schema will be that of an empty object in order to comply with the MCP protocol requirements. Clients must send an empty object ("{}")in response. **Args:** * `message`: A human-readable message explaining what information is needed * `response_type`: The type of the response, which should be a primitive type or dataclass or BaseModel. If it is a primitive type, an object schema with a single "value" field will be generated. #### `set_state` ```python theme={null} set_state(self, key: str, value: Any) -> None ``` Set a value in the session-scoped state store. Values persist across requests within the same MCP session. The key is automatically prefixed with the session identifier. State expires after 1 day to prevent unbounded memory growth. #### `get_state` ```python theme={null} get_state(self, key: str) -> Any ``` Get a value from the session-scoped state store. Returns None if the key is not found. #### `delete_state` ```python theme={null} delete_state(self, key: str) -> None ``` Delete a value from the session-scoped state store. #### `enable_components` ```python theme={null} enable_components(self) -> None ``` Enable components matching criteria for this session only. Session rules override global transforms. Rules accumulate - each call adds a new rule to the session. Later marks override earlier ones (Visibility transform semantics). Sends notifications to this session only: ToolListChangedNotification, ResourceListChangedNotification, and PromptListChangedNotification. **Args:** * `names`: Component names or URIs to match. * `keys`: Component keys to match (e.g., {"tool\:my_tool@v1"}). * `version`: Component version spec to match. * `tags`: Tags to match (component must have at least one). * `components`: Component types to match (e.g., {"tool", "prompt"}). * `match_all`: If True, matches all components regardless of other criteria. #### `disable_components` ```python theme={null} disable_components(self) -> None ``` Disable components matching criteria for this session only. Session rules override global transforms. Rules accumulate - each call adds a new rule to the session. Later marks override earlier ones (Visibility transform semantics). Sends notifications to this session only: ToolListChangedNotification, ResourceListChangedNotification, and PromptListChangedNotification. **Args:** * `names`: Component names or URIs to match. * `keys`: Component keys to match (e.g., {"tool\:my_tool@v1"}). * `version`: Component version spec to match. * `tags`: Tags to match (component must have at least one). * `components`: Component types to match (e.g., {"tool", "prompt"}). * `match_all`: If True, matches all components regardless of other criteria. #### `reset_visibility` ```python theme={null} reset_visibility(self) -> None ``` Clear all session visibility rules. Use this to reset session visibility back to global defaults. Sends notifications to this session only: ToolListChangedNotification, ResourceListChangedNotification, and PromptListChangedNotification.