.vscode — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited .vscode (MCP Server) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A Model Context Protocol (MCP) server that provides latitude/longitude coordinates for cities and locations using the OpenStreetMap Nominatim API.
uvx geocode-mcpInstall the package from PyPI using uvx (recommended):
uvx geocode-mcpOr install with pip:
pip install geocode-mcpAdd to your MCP client configuration:
{
"mcpServers": {
"geocoding": {
"command": "uvx",
"args": ["geocode-mcp"]
}
}
}See the config/ directory for specific examples for different tools.
mcp_geocoding_get_coordinatesGet latitude and longitude coordinates for a city or location.
Parameters:
location (required): City name, address, or location (e.g., "New York", "Paris, France", "123 Main St, Seattle")limit (optional): Maximum number of results to return (default: 1, max: 10)Example Usage:
Get coordinates for Tokyo, Japan
Find the latitude and longitude of London, UK
What are the coordinates for New York City?
Get coordinates for "1600 Pennsylvania Avenue, Washington DC" with limit 5Response Format:
{
"query": "Tokyo, Japan",
"results_count": 1,
"coordinates": [
{
"latitude": 35.6762,
"longitude": 139.6503,
"display_name": "Tokyo, Japan",
"place_id": "282885117",
"type": "city",
"class": "place",
"importance": 0.9,
"bounding_box": {
"south": 35.619,
"north": 35.739,
"west": 139.619,
"east": 139.682
}
}
]
}Copy the configuration from config/cursor-mcp.json to your Cursor MCP settings.
Copy the configuration from config/vscode-mcp.json to your VS Code MCP settings.
Copy the configuration from config/claude-desktop.json to your Claude Desktop config file.
See the config README for detailed setup instructions.
# Clone the repository
git clone https://github.com/X-McKay/geocode-mcp.git
cd geocode-mcp
# Install with development dependencies
pip install -e ".[dev]"# Run all tests
pytest
# Run with coverage
pytest --cov=src/geocode_mcp --cov-report=html
# Run specific test files
pytest tests/test_geocoding.py -v
pytest tests/test_mcp_server.py -v# Format code
ruff format
# Lint code
ruff check
# Run all checks
ruff check && ruff format --checkFor local development and testing, you can run the server directly:
python -m geocode_mcp.serverOr use the development configuration in your MCP client:
{
"mcpServers": {
"geocoding": {
"command": "python",
"args": ["-m", "geocode_mcp.server"],
"cwd": "/path/to/geocode-mcp",
"env": {
"PYTHONPATH": "/path/to/geocode-mcp/src"
}
}
}
}geocode-mcp/
├── src/geocode_mcp/ # Main source code
│ └── server.py # MCP server implementation
├── tests/ # Test suite
│ ├── test_geocoding.py # Geocoding functionality tests
│ ├── test_mcp_server.py # MCP server integration tests
│ ├── test_mcp.py # MCP protocol tests
│ └── test_vscode.py # VS Code integration tests
├── config/ # Configuration examples
│ ├── cursor-mcp.json # Cursor configuration
│ ├── vscode-mcp.json # VS Code configuration
│ ├── claude-desktop.json # Claude Desktop configuration
│ └── README.md # Configuration guide
├── docs/ # Documentation
├── pyproject.toml # Project configuration
├── requirements.txt # Production dependencies
├── requirements-dev.txt # Development dependencies
└── README.md # This fileasync def geocode_location(location: str, limit: int = 1) -> dict[str, Any]:
"""
Geocode a location using OpenStreetMap Nominatim API.
Args:
location: The location to geocode
limit: Maximum number of results (1-10)
Returns:
Dictionary containing query, results_count, and coordinates
"""The server implements the Model Context Protocol and provides the mcp_geocoding_get_coordinates tool for use in MCP-compatible applications.
git checkout -b feature/amazing-feature)pytest)ruff check && ruff format)git commit -m 'Add amazing feature')git push origin feature/amazing-feature)See CONTRIBUTING.md for more details.
This project is licensed under the MIT License - see the LICENSE file for details.
make lint
make format
make type-check
make check-all
### Testing
make test
make test-cov
pytest tests/test_geocoding.py -v # Geocoding tests pytest tests/test_mcp.py -v # MCP server tests python tests/test_mcp_server.py # Integration tests python tests/test_vscode.py # VSCode tests
### Installation
make install
make install-dev
## Configuration
### Cursor Integration
See [Cursor Integration Guide](docs/cursor-integration.md) for detailed setup instructions.
### VSCode Integration
Run the VSCode integration tests:python tests/test_vscode.py
## API Reference
### Geocoding Functionasync def geocode_location(location: str, limit: int = 1) -> dict[str, Any]: """Geocode a location using Nominatim API."""
### MCP Server
The server provides the `get_coordinates` tool that can be called via the MCP protocol.
## Contributing
1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Run tests: `make test`
5. Run linting: `make lint`
6. Submit a pull request
See [CONTRIBUTING.md](CONTRIBUTING.md) for more details.
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## Acknowledgments
- [OpenStreetMap](https://www.openstreetmap.org/) for providing the Nominatim geocoding service
- [MCP](https://modelcontextprotocol.io/) for the protocol specification mkdir mcp-geocoding-server-python
cd mcp-geocoding-server-pythonCopy each file section above into files with the respective names
pip install -r requirements.txt python geocoding_server.pyAdd to your MCP client (like Claude Desktop) configuration:
{
"mcpServers": {
"geocoding": {
"command": "python",
"args": ["/full/path/to/mcp-geocoding-server-python/geocoding_server.py"]
}
}
}~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.