> ## Documentation Index > Fetch the complete documentation index at: https://gofastmcp.com/llms.txt > Use this file to discover all available pages before exploring further. # run # `fastmcp.server.sampling.run` Sampling types and helper functions for FastMCP servers. ## Functions ### `determine_handler_mode` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} determine_handler_mode(context: Context, needs_tools: bool) -> bool ``` Determine whether to use fallback handler or client for sampling. **Args:** * `context`: The MCP context. * `needs_tools`: Whether the sampling request requires tool support. **Returns:** * True if fallback handler should be used, False to use client. **Raises:** * `ValueError`: If client lacks required capability and no fallback configured. ### `call_sampling_handler` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} call_sampling_handler(context: Context, messages: list[SamplingMessage]) -> CreateMessageResult | CreateMessageResultWithTools ``` Make LLM call using the fallback handler. Note: This function expects the caller (sample\_step) to have validated that sampling\_handler is set via determine\_handler\_mode(). The checks below are safeguards against internal misuse. ### `execute_tools` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} execute_tools(tool_calls: list[ToolUseContent], tool_map: dict[str, SamplingTool], mask_error_details: bool = False, tool_concurrency: int | None = None) -> list[ToolResultContent] ``` Execute tool calls and return results. **Args:** * `tool_calls`: List of tool use requests from the LLM. * `tool_map`: Mapping from tool name to SamplingTool. * `mask_error_details`: If True, mask detailed error messages from tool execution. When masked, only generic error messages are returned to the LLM. Tools can explicitly raise ToolError to bypass masking when they want to provide specific error messages to the LLM. * `tool_concurrency`: Controls parallel execution of tools: * None (default): Sequential execution (one at a time) * 0: Unlimited parallel execution * N > 0: Execute at most N tools concurrently If any tool has sequential=True, all tools execute sequentially regardless of this setting. **Returns:** * List of tool result content blocks in the same order as tool\_calls. ### `prepare_messages` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} prepare_messages(messages: str | Sequence[str | SamplingMessage]) -> list[SamplingMessage] ``` Convert various message formats to a list of SamplingMessage objects. ### `prepare_tools` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} prepare_tools(tools: Sequence[SamplingTool | FunctionTool | TransformedTool | Callable[..., Any]] | None) -> list[SamplingTool] | None ``` Convert tools to SamplingTool objects. Accepts SamplingTool instances, FunctionTool instances, TransformedTool instances, or plain callable functions. FunctionTool and TransformedTool are converted using from\_callable\_tool(), while plain functions use from\_function(). **Args:** * `tools`: Sequence of tools to prepare. Can be SamplingTool, FunctionTool, TransformedTool, or plain callable functions. **Returns:** * List of SamplingTool instances, or None if tools is None. ### `extract_tool_calls` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} extract_tool_calls(response: CreateMessageResult | CreateMessageResultWithTools) -> list[ToolUseContent] ``` Extract tool calls from a response. ### `create_final_response_tool` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} create_final_response_tool(result_type: type) -> SamplingTool ``` Create a synthetic 'final\_response' tool for structured output. This tool is used to capture structured responses from the LLM. The tool's schema is derived from the result\_type. ### `sample_step_impl` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} sample_step_impl(context: Context, messages: str | Sequence[str | SamplingMessage]) -> SampleStep ``` Implementation of Context.sample\_step(). Make a single LLM sampling call. This is a stateless function that makes exactly one LLM call and optionally executes any requested tools. ### `sample_impl` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} sample_impl(context: Context, messages: str | Sequence[str | SamplingMessage]) -> SamplingResult[ResultT] ``` Implementation of Context.sample(). Send a sampling request to the client and await the response. This method runs to completion automatically, executing a tool loop until the LLM provides a final text response. ## Classes ### `SamplingResult` Result of a sampling operation. **Attributes:** * `text`: The text representation of the result (raw text or JSON for structured). * `result`: The typed result (str for text, parsed object for structured output). * `history`: All messages exchanged during sampling. ### `SampleStep` Result of a single sampling call. Represents what the LLM returned in this step plus the message history. **Methods:** #### `is_tool_use` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} is_tool_use(self) -> bool ``` True if the LLM is requesting tool execution. #### `text` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} text(self) -> str | None ``` Extract text from the response, if available. #### `tool_calls` ```python theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}} tool_calls(self) -> list[ToolUseContent] ``` Get the list of tool calls from the response.