Skip to main content
Glama
grab

TinyMCP

Official
by grab

TinyMCP

A lightweight MCP router for FastAPI.

Quick Start

from tinymcp import create_mcp_router, mcp_tool

@mcp_tool(description="Get current time")
def get_time() -> str:
    from datetime import datetime
    return datetime.now().isoformat()

@mcp_tool(description="Get user data with structured output")
def get_user_data():
    return {
        "content": [{"type": "text", "text": "User data retrieved"}],
        "structured": {"user_id": 123, "email": "user@example.com"}
    }

# Add to FastAPI
app.include_router(create_mcp_router(name="My App"))

# Custom prefix (default: "/mcp")
app.include_router(create_mcp_router(name="My App", prefix="/my-mcp"))

Related MCP server: ZepAI Memory Layer MCP Server

Quick Demo

Once you have this repo cloned, from root, run the following (install the missing dev dependencies as required)

uv run python docs/sample_server/simple_fastapi_server.py

Note on Authentication

Authentication has been intentionally left out of TinyMCP to keep it... tiny. Any auth that can be setup with FastAPI in general can be setup with this. However, for MCP server to interact with most MCP clients like cursor, several specific configurations, endpoints etc. are required. If you have an existing OAuth mechanism in your FastAPI server, it is quite easy to make it work for the TinyMCP server as well. See oauth_integration_guide.md for a complete setup guide.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

No tool schema history has been recorded yet.

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    A zero-configuration tool that automatically converts FastAPI endpoints into Model Context Protocol (MCP) tools, enabling AI systems to interact with your API through natural language.
    2
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Exposes FastAPI endpoints as Model Context Protocol (MCP) tools while preserving existing authentication, schemas, and documentation. It enables seamless integration of FastAPI services into MCP ecosystems using a native ASGI transport layer.
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/grab/tinymcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server