FastMCP MCP — Сценарии использования, Установка & Живое демо

Зачем использовать

Ключевые функции

Single decorator per tool: @mcp.tool or @mcp.resource
Type hints become JSON schemas — no manual schema writing
Async-first, supports sync too — stdlib typing works
Transports built in: stdio (for desktop clients), SSE / streamable HTTP (for remote)

Живое демо

Как выглядит на практике

fastmcp.replay ▶ готово

0/0

Установка

Выберите клиент

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "fastmcp": {
      "command": "uvx",
      "args": [
        "fastmcp"
      ]
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "fastmcp": {
      "command": "uvx",
      "args": [
        "fastmcp"
      ]
    }
  }
}

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "fastmcp": {
      "command": "uvx",
      "args": [
        "fastmcp"
      ]
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "fastmcp": {
      "command": "uvx",
      "args": [
        "fastmcp"
      ]
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "fastmcp",
      "command": "uvx",
      "args": [
        "fastmcp"
      ]
    }
  ]
}

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json

{
  "context_servers": {
    "fastmcp": {
      "command": {
        "path": "uvx",
        "args": [
          "fastmcp"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

claude mcp add fastmcp -- uvx fastmcp

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: FastMCP

Expose an internal REST API as an MCP in under an hour

👤 Backend engineers with an existing Python service ⏱ ~45 min intermediate

Когда использовать: You have a company API that agents should be able to call, and you don't want to write a client spec from scratch.

Предварительные требования

Python 3.10+ — python --version
uv installed — curl -LsSf https://astral.sh/uv/install.sh | sh

Поток

Bootstrap the project

Scaffold a FastMCP server project called 'acme-api-mcp' with one starter tool. Use uv for dependency management.✓ Скопировано

→ pyproject.toml + server.py with a working @mcp.tool example
Wrap the 3 highest-value endpoints

My internal API has endpoints /orders/{id}, /customers/search, /invoices/{id}/pdf. Write a FastMCP tool for each, using httpx.AsyncClient and reading AUTH_TOKEN from env.✓ Скопировано

→ 3 decorated functions with type hints + docstrings that become tool descriptions
Test locally with the MCP Inspector

Run the server with uv run mcp dev server.py. Open the inspector and call each tool with a realistic input.✓ Скопировано

→ Tools return expected JSON, no stack traces

Итог: A working MCP server you can point Claude Desktop or any MCP client at.

Подводные камни

Secrets leak into tool descriptions because you printed them in docstrings — Use docstrings to describe behavior, not examples with real tokens. Load secrets via os.environ and never echo them in errors
Async + sync mixed, causes event loop errors — Pick one — if your HTTP client is async, make the whole tool async; don't call asyncio.run inside a tool

Expose company docs as MCP resources for RAG

👤 Platform engineers building agent infra ⏱ ~30 min intermediate

Когда использовать: You want the agent to auto-discover and pull company knowledge without tool calls for every file.

Поток

Define a resource listing

Define a FastMCP resource at URI docs://{path} that lists all markdown files under ./docs/ and returns their content on read.✓ Скопировано

→ Resource registered, inspector shows list
Add a template resource

Add a resource template docs://{category}/{slug} that returns the matching file. Document valid {category} values.✓ Скопировано

→ Template registered, parameterized fetches work
Test in a real client

Connect Claude Desktop to the server. Verify the Resources menu lists all docs and content loads.✓ Скопировано

→ Resources appear as attachable context

Итог: A resource-backed knowledge surface the agent can pull from natively — cleaner than tool calls for static content.

Подводные камни

Large resource lists overwhelm the client's UI — Paginate or filter in your list endpoint; not every file needs to be surfaced

Deploy a FastMCP server as a remote SSE endpoint

👤 Platform engineers serving multiple teams ⏱ ~60 min advanced

Когда использовать: Multiple devs need the same MCP — host it once, don't make everyone run stdio locally.

Предварительные требования

A container host (Cloud Run, Fly, Railway) — Any Docker-capable runtime works

Поток

Switch transport to SSE

Modify server.py to run mcp.run(transport='sse', host='0.0.0.0', port=8080). Add a minimal Dockerfile.✓ Скопировано

→ Local curl localhost:8080/sse shows SSE handshake
Deploy behind auth

Deploy to Cloud Run with IAM auth. Front the /sse endpoint with a header-based auth check in a FastAPI middleware.✓ Скопировано

→ Public URL with 401 on unauth'd requests
Wire clients

Share the connection command with teammates: npx -y mcp-remote https://mcp.acme.com/sse. Verify their Claude Desktop picks up the tools.✓ Скопировано

→ Team members' clients see the same tools

Итог: A shared remote MCP — one codebase, many users, easy to update.

Подводные камни

SSE connections drop behind some corporate proxies — Use streamable HTTP transport instead (newer spec) or document a VPN/direct-path requirement

Сочетать с: cloud-run

Комбинации

Сочетайте с другими MCP — эффект x10

fastmcp + cloud-run

Build once, deploy to Cloud Run, share with the team

Wrap my internal pricing API as a FastMCP server, containerize it, and deploy to Cloud Run with IAM auth.✓ Скопировано

fastmcp + fastapi-mcp

Compare approaches — FastMCP for greenfield, fastapi-mcp for existing FastAPI apps

I have an existing FastAPI service. Should I add fastapi-mcp to expose it or rewrite in FastMCP? Compare based on my routes.✓ Скопировано

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
@mcp.tool	decorated function with typed signature	Wrap any function you want agents to call	free
@mcp.resource	URI template + function	Expose readable content (docs, config, data snapshots)	free
@mcp.prompt	decorated function returning Message[]	Provide reusable multi-turn prompt scaffolds to clients	free
mcp.run	transport: 'stdio'\|'sse'\|'streamable-http', host?, port?	Entry point — call at end of your main script	free
Context (ctx) parameter	inject ctx: Context into any tool	Long-running tools that need to stream progress or log	free

Стоимость и лимиты

Во что обходится

Квота API: None — this is a framework, not a service
Токенов на вызов: Your server runs any LLM calls; framework overhead is negligible
Деньги: Free, open source
Совет: Use resources instead of tools for static content — resources are cheaper in tokens because they're pre-declared

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: Your choice — env vars are idiomatic; load secrets at process start, not per call

Исходящий трафик: Wherever your tool functions reach out to

Устранение неполадок

Частые ошибки и исправления

Tool schema missing required fields in the client

Your function params need type hints. Plain def foo(x) generates a useless schema — use def foo(x: str) with a docstring.

Проверить: Run `uv run mcp dev server.py` and check the Inspector's tool schema

Server starts but client sees 0 tools

You're mixing stdio with SSE misconfiguration. For Claude Desktop use transport='stdio'; for mcp-remote use 'sse'.

`ImportError: No module named 'fastmcp'`

Install with uv pip install fastmcp or add to pyproject.toml dependencies. Check that you're running the server from the same venv.

Проверить: uv pip show fastmcp

Async tool hangs on first call

You imported sync httpx inside an async tool. Use httpx.AsyncClient with async with — never mix.

Альтернативы

FastMCP в сравнении

Альтернатива	Когда использовать	Компромисс
TypeScript MCP SDK	You're a TS/Node shop and want to stay there	Official, well-maintained, similar DX — just different language
fastapi-mcp	You already have a FastAPI app and want to expose routes as tools	Less control over the MCP surface but zero-refactor for existing services
csharp-sdk	.NET shop	First-party, but smaller ecosystem of examples

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills