mirror of
https://github.com/PrefectHQ/fastmcp.git
synced 2026-08-13 00:59:10 +02:00
a1cf2aff6eCo-authored-by: marvin-context-protocol[bot] <225465937+marvin-context-protocol[bot]@users.noreply.github.com>
80 lines
2.5 KiB
Text
80 lines
2.5 KiB
Text
---
|
|
title: sampling_tool
|
|
sidebarTitle: sampling_tool
|
|
---
|
|
|
|
# `fastmcp.server.sampling.sampling_tool`
|
|
|
|
|
|
SamplingTool for use during LLM sampling requests.
|
|
|
|
## Classes
|
|
|
|
### `SamplingTool` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/sampling/sampling_tool.py#L16" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
|
|
A tool that can be used during LLM sampling.
|
|
|
|
SamplingTools bundle a tool's schema (name, description, parameters) with
|
|
an executor function, enabling servers to execute agentic workflows where
|
|
the LLM can request tool calls during sampling.
|
|
|
|
In most cases, pass functions directly to ctx.sample():
|
|
|
|
def search(query: str) -> str:
|
|
'''Search the web.'''
|
|
return web_search(query)
|
|
|
|
result = await context.sample(
|
|
messages="Find info about Python",
|
|
tools=[search], # Plain functions work directly
|
|
)
|
|
|
|
Create a SamplingTool explicitly when you need custom name/description:
|
|
|
|
tool = SamplingTool.from_function(search, name="web_search")
|
|
|
|
|
|
**Methods:**
|
|
|
|
#### `run` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/sampling/sampling_tool.py#L47" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
run(self, arguments: dict[str, Any] | None = None) -> Any
|
|
```
|
|
|
|
Execute the tool with the given arguments.
|
|
|
|
**Args:**
|
|
- `arguments`: Dictionary of arguments to pass to the tool function.
|
|
|
|
**Returns:**
|
|
- The result of executing the tool function.
|
|
|
|
|
|
#### `from_function` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/sampling/sampling_tool.py#L77" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
from_function(cls, fn: Callable[..., Any]) -> SamplingTool
|
|
```
|
|
|
|
Create a SamplingTool from a function.
|
|
|
|
The function's signature is analyzed to generate a JSON schema for
|
|
the tool's parameters. Type hints are used to determine parameter types.
|
|
|
|
**Args:**
|
|
- `fn`: The function to create a tool from.
|
|
- `name`: Optional name override. Defaults to the function's name.
|
|
- `description`: Optional description override. Defaults to the function's docstring.
|
|
- `sequential`: If True, this tool requires sequential execution and prevents
|
|
parallel execution of all tools in the batch. Set to True for tools
|
|
with shared state, file writes, or other operations that cannot run
|
|
concurrently. Defaults to False.
|
|
|
|
**Returns:**
|
|
- A SamplingTool wrapping the function.
|
|
|
|
**Raises:**
|
|
- `ValueError`: If the function is a lambda without a name override.
|
|
|