drio
Open app

MCP Server Demo with Goose

Source

Catalog onlyCatalog onlySTDIO

Overview

MCP Server Demo with Goose is a project that demonstrates how to set up an MCP Server using Python and integrate it with Goose or Claude Desktop to interact with AI tools.

To use the MCP Server Demo, follow the setup instructions, install the required packages, and run the development server using the provided commands.

  • Easy setup of an MCP Server using Python. - Integration with AI tools like Goose and Claude Desktop. - Step-by-step instructions for installation and running the server.
  1. Setting up a local development environment for AI tool integration.
  2. Experimenting with AI interactions using Goose or Claude.
  3. Learning how to create and manage an MCP Server.

Add to your AI client

Use these steps to connect MCP Server Demo with Goose in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server-demo-schwannden": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-demo-schwannden"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-server-demo-schwannden": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-demo-schwannden"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-server-demo-schwannden": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-demo-schwannden"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-server-demo-schwannden": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-demo-schwannden"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-server-demo-schwannden": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-demo-schwannden"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-server-demo-schwannden": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-demo-schwannden"
      ]
    }
  }
}

FAQ

What is required to set up the MCP Server?

You need to install the uv package manager and follow the setup instructions provided in the documentation.

Can I use this project for production?

This demo is primarily for development and learning purposes; further modifications may be needed for production use.

Where can I find more information?

You can refer to the [Original Post](https://medium.com/@schwanndenkuo/ai-agent-0-%E5%88%B0-1-mcp-server-with-goose-00741f7cdb6c) for more details.