sanbuphy/nanoMCP

If you can read ~200 lines of Python, you understand MCP.

29
/ 100
Experimental

This project helps developers understand and implement the Model Context Protocol (MCP) for connecting large language models (LLMs) with external tools. It demonstrates how to create an MCP server that exposes simple tools (like add, multiply, weather) and various MCP clients (stdio, SSE, Streamable HTTP) that allow an LLM to call these tools. The examples are designed for developers who want to integrate LLMs with custom functionalities or external data sources.

Use this if you are a developer learning how to enable an LLM to interact with external tools using the Model Context Protocol (MCP) and want clear, self-contained examples.

Not ideal if you are an end-user looking for a ready-to-use application; this is a toolkit for developers to build such applications.

LLM-integration tool-calling agentic-AI protocol-implementation developer-toolkit
No License No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 3 / 25
Community 9 / 25

How are scores calculated?

Stars

32

Forks

3

Language

Python

License

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/sanbuphy/nanoMCP"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.