Developer Tools MCP Server

An MCP (Model Context Protocol) server that provides developer-focused tools for searching packages, repositories, and coding Q&A — all using public APIs with no API keys required.

Tools

1. search_pypi

Search PyPI for a Python package and get its name, description, latest version, and pip install command.

Parameters:

• package_name (str): The name of the package to search for (e.g. "requests")

Example response:

{
  "name": "requests",
  "description": "Python HTTP for Humans.",
  "latest_version": "2.31.0",
  "pip_install": "pip install requests"
}

2. get_github_repo

Fetch public info about a GitHub repository including stars, description, language, and last updated date.

Parameters:

• owner (str): The repository owner (e.g. "pallets")

• repo (str): The repository name (e.g. "flask")

Example response:

{
  "full_name": "pallets/flask",
  "description": "The Python micro framework for building web applications.",
  "stars": 65000,
  "language": "Python",
  "last_updated": "2024-01-15T10:30:00Z",
  "open_issues": 5,
  "forks": 15000,
  "url": "https://github.com/pallets/flask"
}

3. search_stackoverflow

Search Stack Overflow for coding questions and return the top 3 results with titles, links, and scores.

Parameters:

• query (str): The search query (e.g. "python async await")

Example response:

{
  "query": "python async await",
  "result_count": 3,
  "results": [
    {
      "title": "How to use async/await in Python?",
      "link": "https://stackoverflow.com/questions/...",
      "score": 150,
      "answer_count": 5,
      "is_answered": true
    }
  ]
}

4. check_package_compatibility

Check if a Python package supports a specific Python version using PyPI classifier metadata.

Parameters:

• package_name (str): The package name (e.g. "requests")

• python_version (str): The Python version to check (e.g. "3.12")

Example response:

{
  "package": "requests",
  "latest_version": "2.31.0",
  "python_version_checked": "3.12",
  "is_compatible": true,
  "supported_python_versions": ["3", "3.8", "3.9", "3.10", "3.11", "3.12"],
  "requires_python": ">=3.8",
  "compatibility_source": "classifiers"
}

Related MCP server: Smart Search MCP

Setup

# Install dependencies
pip install -r requirements.txt

# Run the server directly
python mcp_server.py

# Run tests
pytest test_server.py -v

Connect to Claude Desktop

Add the following to your Claude Desktop configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "developer-tools": {
      "command": "python",
      "args": ["/absolute/path/to/mcp_server.py"]
    }
  }
}

Replace /absolute/path/to/mcp_server.py with the actual absolute path to the file.

After saving, restart Claude Desktop. The four tools will appear in the tools menu (hammer icon).

Connect to Claude Code

Add to your Claude Code settings (.claude/settings.json or project-level):

{
  "mcpServers": {
    "developer-tools": {
      "command": "python",
      "args": ["/absolute/path/to/mcp_server.py"]
    }
  }
}

Or use the CLI:

claude mcp add developer-tools python /absolute/path/to/mcp_server.py