🏓 MCP Ping-Pong Server with FastAPI

What is 🏓 MCP Ping-Pong Server with FastAPI?

An experimental and educational Ping-Pong server that demonstrates MCP (Model Context Protocol) calls through a FastAPI/FastMCP backend. It provides a simple command‑handling system (ping, pong, count) accessible via API endpoints or Server‑Sent Events (SSE), making it a learning tool for understanding remote MCP integrations.

How to use 🏓 MCP Ping-Pong Server with FastAPI?

Install dependencies with poetry install. Run python mcp-api-server.py to start the FastAPI server on http://localhost:8080 and open mcp-api-client.html in a browser for the UI, or use the API directly. For SSE transport, run python mcp-sse-server.py and then python mcp-sse-client.py to interact via the command line with commands like ping, pong, and count.

Key features of 🏓 MCP Ping-Pong Server with FastAPI

• FastAPI/FastMCP backend for remote MCP calls.
• MCP integration for command handling (ping, pong, count).
• Thread-safe session management.
• API endpoints for GET (prompt retrieval) and POST (tool invocation).
• SSE transport support for real‑time communication.

Use cases of 🏓 MCP Ping-Pong Server with FastAPI

• Learning how to build and run an MCP server with FastAPI.
• Demonstrating remote MCP calls via HTTP and SSE transports.
• Experimenting with thread-safe session handling in MCP.
• Teaching MCP concepts through a simple, interactive command loop.

FAQ from 🏓 MCP Ping-Pong Server with FastAPI

What commands does the server support?

The MCP server supports three commands: ping, pong, and count. The sample output shows ping returns pong, pong returns ping, and count returns the current count (e.g., 2).

How do I install and run the server?

Install dependencies with poetry install. For the API server, run python mcp-api-server.py. For SSE, run python mcp-sse-server.py. The client for SSE is started with python mcp-sse-client.py.

Is there a graphical user interface?

Yes, the repository includes mcp-api-client.html which you can open in a browser to interact with the API server via a simple UI.

What transport options are available?

Two transport methods are demonstrated: HTTP API (GET/POST endpoints at http://localhost:8080) and Server-Sent Events (SSE) using separate server and client scripts.

What dependencies does the server require?

All Python dependencies are managed via Poetry. The key libraries include FastAPI and FastMCP (for the backend), along with other runtime dependencies listed in the pyproject.toml file.