fastmcp

Build, test, and deploy MCP servers in Python using FastMCP templates and CLI.

Updated Apr 18, 2026
One-click install
npx skills add https://github.com/azaanaliraza/operarius --skill fastmcp-azaanaliraza
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fastmcp
Source: https://github.com/azaanaliraza/operarius/tree/main/src-tauri/bin/hermes/optional-skills/mcp/fastmcp
Command: npx skills add https://github.com/azaanaliraza/operarius --skill fastmcp-azaanaliraza

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires fastmcp, httpx, and includes scripts (resource) and references (resource) components.

What problem does it solve? Building a Model Context Protocol server from scratch involves boilerplate, unclear tool design, and uncertain validation steps. This Skill provides ready-made FastMCP templates, a scaffolding script, and a CLI-driven workflow so you can create, test, install, and deploy MCP servers without guesswork. ## Core Features & Use Cases - Starter Templates: Three production-shaped templates cover the most common server types: REST API wrappers with auth headers, read-only SQLite database servers, and text-file inspection servers. - Scaffolding Script: The scaffold_fastmcp.py script copies a template and injects your server name, producing a working Python file in one command. - CLI Validation Workflow: Guides you through fastmcp inspect, fastmcp list, and fastmcp call to verify every tool before installing into Claude Code, Claude Desktop, Cursor, or deploying over HTTP. - Use Case: You need to expose your company's internal REST API to an AI assistant. Scaffold the API wrapper template, implement two or three typed tools, validate them with the FastMCP CLI, then install the server into your MCP client. ## Quick Start Ask the AI to scaffold a new FastMCP server from the API wrapper template named after your service and validate it with the FastMCP CLI.

Frequently Asked Questions about fastmcp

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

FAQPage Schema
How do I build an MCP server in Python with FastMCP?▼

Install fastmcp with pip, scaffold a starter template such as the API wrapper or database server, then define tools with the @mcp.tool decorator using typed parameters and docstrings. Validate the server with fastmcp inspect and fastmcp call before installing it into a client.

How do I test a FastMCP server before deploying it?▼

Run fastmcp inspect on your server file to verify it loads, then use fastmcp list to enumerate tools and fastmcp call to execute each tool with real arguments. For HTTP transport, start the server with fastmcp run using the http transport and call it against the local /mcp endpoint.

Can I install a FastMCP server into Claude Code or Cursor?▼

Yes, the FastMCP CLI supports direct installation with commands like fastmcp install claude-code, fastmcp install claude-desktop, and fastmcp install cursor. Client installs run in isolated environments, so declare extra dependencies with flags such as --with or editable installs.

Why does fastmcp inspect fail on my server file?▼

Inspection usually fails when the file has import-time side effects that crash, the FastMCP object name does not match the file:object reference, or optional template dependencies like httpx are missing. Fix imports, confirm the object name, and install missing packages.

When should I use FastMCP versus connecting an existing MCP server?▼

Use FastMCP when you are creating a new server or wrapping an API, database, or file workflow as MCP tools. If the server already exists and only needs to be connected to a client like Hermes, configure it directly rather than rebuilding it.