fastmcp

Build and validate FastMCP MCP servers in Python.

Updated May 26, 2026
One-click install
npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill fastmcp-ruiyangruiyi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fastmcp
Source: https://github.com/ruiyangruiyi/hermes-agent/tree/main/optional-skills/mcp/fastmcp
Command: npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill fastmcp-ruiyangruiyi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

FastMCP turns a Python API, database, or file workflow into an MCP server so other MCP clients (like Claude Code, Cursor, or Claude Desktop) can reliably call your tools and fetch your resources.

Core Features & Use Cases

  • Scaffold MCP servers from templates: Start from API wrapper, SQLite read-only database, or file processor templates and generate a working server implementation.
  • Expose tools, resources, and prompts: Implement @mcp.tool functions first, then add optional @mcp.resource and @mcp.prompt only when they provide reusable value.
  • Validate and deploy safely: Use FastMCP CLI commands to inspect, list, and call tools locally before installing into an MCP client or deploying via HTTP.

Quick Start

Use the skill to scaffold an API-wrapping MCP server by asking: "Create a FastMCP MCP server for my REST API using the API wrapper template, then inspect it and list its tools."

Frequently Asked Questions about fastmcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I expose a Python REST API as an MCP server for Claude Code?

Build an MCP server using FastMCP by defining a Python server object and typed `@mcp.tool` functions with JSON-safe returns. Validate locally with FastMCP CLI commands before HTTP deployment or client installation.

Can I provide read-only SQLite database queries through an MCP server?

Yes, you can provide read-only SQLite queries by scaffolding an MCP server from the SQLite read-only database template, exposing safe query functions as `@mcp.tool` endpoints, and verifying them with the FastMCP CLI.

What is the best way to validate MCP server tools locally before deployment?

Validate MCP server tools locally by running FastMCP CLI commands to inspect the server object, list defined `@mcp.tool` functions, and call tools to verify JSON-safe returns before deploying to an MCP client.

Does FastMCP support exposing resources and prompts alongside tools?

Yes, FastMCP supports exposing resources and prompts alongside tools. You implement `@mcp.tool` functions first, then add optional `@mcp.resource` and `@mcp.prompt` decorators only when they provide reusable value for MCP clients.

How do I inspect and list tools on a Python MCP server?

You inspect and list tools on a Python MCP server by running local FastMCP CLI verification steps, which allow you to inspect the server object, list its registered `@mcp.tool` functions, and call them directly.