projectfour-expert

One Model Context Protocol (MCP) server

Prerequisites

1. Install uv from Astral or the GitHub README
2. Install Python using uv python install 3.13

Installation

Install the MCP server:

uv tool install mylabs-mcp.projectfour-expert --force 

Add the server to your MCP client config (e.g. ~/.cursor-server/data/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json):

{
  "mcpServers": {
    "mylabs_mcp.projectfour_expert": {
      "command": "uvx",
      "args": [
        "--from",
        "mylabs-mcp-projectfour-expert",
        "projectfour-expert"
      ],
      "env": {
        "SHELL": "/usr/bin/zsh"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Development

1. Set up the development environment:

uv sync --all-groups

2. Run the server:

uv run mylabs-mcp.projectfour-expert/server.py

3. Install pre-commit hooks:

GIT_CONFIG=/dev/null pre-commit install

Running the Server

Run the server with default stdio transport:

uv run mylabs-mcp.projectfour-expert/server.py

Or with SSE transport on a specific port:

uvx projectfour-expert/server.py --sse --port 8888

Customizing the Server

1. Edit projectfour_expert/server.py to implement your MCP tools and resources
2. Add dependencies to pyproject.toml with uv add <dependency>
3. Update tests and documentation as needed
4. Build the project: uv build
5. Push the changes: git push
6. Create a release: uv run cz bump
7. Tag the release: git push --tags