MCP Quickstart Resources
Example Model Context Protocol servers and clients in five languages, written as companion code for the official MCP server and client tutorials.
MCP Quickstart Resources holds example servers and clients for the Model Context Protocol in five languages, each living in its own directory with a README covering prerequisites, setup and how to run it. The servers all expose the same two tools, a weather forecast tool and a weather alert tool backed by the US National Weather Service API, and communicate over stdio.
The companion clients are LLM-powered chatbots that launch a server, list its tools, and start an interactive chat loop in which Claude can call those tools; a client from one language can drive a server written in another. Running the clients needs an Anthropic API key, though without one each client still connects and lists the server's tools before exiting, so the MCP wiring itself can be checked without credentials.
A smoke-test suite in the repository verifies that every server starts, answers MCP requests, and returns tool results that validate against each tool's advertised schema, and that every client can connect. Building across all five languages needs Node.js, Python with uv, Go, Rust and Ruby toolchains.