MCP Server Demo

A Python MCP Server demonstrating integration with Goose/Claude Desktop for AI tool interactions.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "schwannden-mcp-server-demo": {
      "command": "mcp",
      "args": [
        "dev",
        "src/mcp_server_demo/server.py"
      ]
    }
  }
}

You are running an MCP Server that connects your AI tools with your client apps. This server lets you expose AI-enabled capabilities to end users through a consistent MCP protocol, enabling tooling like Goose or Claude Desktop to interact with AI tools through a local or remote endpoint.

How to use

You run the MCP server locally and connect a client to it to perform actions and get results. Start the server in development mode and then interact with it through your preferred MCP client. The flow is straightforward: launch the server, then issue requests from the client to perform tasks, receive responses, and iterate.

How to install

Prerequisites include having the UV package manager available on your system. Install UV according to your platform’s setup instructions, then proceed with the following steps to prepare and run the server in development mode.

uv sync
pre-commit install

Once the setup steps are complete, you can start the development server with the MCP command shown in the run instructions.

Notes

This project demonstrates integrating an MCP Server written in Python with Goose or Claude Desktop to enable interaction with AI tools. You can run the server in development mode and test integration with supported clients.

Development server command

dev src/mcp_server_demo/server.py