What is agentic sampling in FastMCP?

Agentic sampling allows a server to pass tools to an LLM during a sampling request, enabling the model to call those tools autonomously as part of its reasoning process.

Can I use Redis for storage with FastMCP?

Yes, FastMCP supports multiple backends including Redis for distributed production environments, alongside Memory and Disk-based storage options.

Is FastMCP compatible with FastAPI?

Yes, FastMCP provides ASGI integration and lifespan management, making it easy to embed within FastAPI or Starlette applications.

Does FastMCP support long-running tasks?

Yes, version 2.14.0+ includes native support for background tasks via the Docket scheduler, allowing for progress tracking without blocking the client.

What is FastMCP used for?

FastMCP is a Python framework used to build servers that follow the Model Context Protocol (MCP), enabling LLMs like Claude to securely access custom tools, data resources, and prompts.

FastMCP Python Framework

Name: FastMCP Python Framework
Author: jezweb

byjezweb

•

117

•

API開発

Builds robust, production-ready Model Context Protocol (MCP) servers in Python to expose tools and resources to LLMs.

FastMCP is a high-level Python framework designed to streamline the creation of Model Context Protocol (MCP) servers, allowing developers to expose custom tools, data resources, and prompts to Large Language Models like Claude. It provides a rich feature set including asynchronous tool execution, persistent storage backends like Redis and Disk, a modular middleware system for logging and rate limiting, and advanced context features such as agentic sampling and background tasks. It is the ideal solution for developers building secure, scalable, and complex integrations between Python-based services and AI agents.

主な機能

01Pluggable storage backends including Memory, Disk, Redis, and encrypted options

02117 GitHub stars

03Native background task support via Docket for long-running operations with progress tracking

04Agentic sampling allowing LLMs to utilize tools within their own reasoning loops

05Built-in middleware for timing, caching, logging, and rate limiting

06Asynchronous tool, resource, and prompt definition with Pydantic type validation

ユースケース

01Implementing long-running data processing workflows that provide real-time status updates to the user

02Creating custom toolkits that allow Claude to interact with internal proprietary databases or APIs

03Deploying secure, OAuth-protected MCP servers to production environments or FastMCP Cloud

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jezweb/claude-skills fastmcp

For use in Claude.ai and ChatGPT

Download Skill