catastro_mcp_server

This MCP server provides access to official Catastro data via two service families: OVC / WCF JSON endpoints (Catastro) for street networks, cadastral references, and conversion between RC and coordinates; and INSPIRE WFS CP endpoints for parcel geometry and diagnostic utilities (GetCapabilities / DescribeFeatureType). The tools are designed to be MCP-compatible, enabling integration with BIM/GIS/AECO workflows and automation pipelines. Typical use cases include enriching models with cadastral geometry, auditing parcels, and programmatically querying addresses, streets, and RCs. You can call tools such as obtener_provincias, obtener_municipios, obtener_vias, obtener_numeros, dcnp_por_direccion, dcnp_por_rc, rc_a_coordenadas, coordenadas_a_rc, and wfs_cp_get_capabilities along with related feature-type and parcel retrieval utilities to obtain structured results or GML/GeoJSON data for downstream processing.

Prerequisites:

• Python 3.8+ installed on your system
• Internet access to fetch dependencies
• Access to a shell/terminal

Installation steps:

1. Create a Python virtual environment (optional but recommended):

python3 -m venv venv
source venv/bin/activate  # Linux/macOS
venv\Scripts\activate     # Windows

2. Install the MCP server package (assuming the repository name is catastro_mcp_server and is published as a package named catastro_mcp_server, or install from source):

pip install catastro_mcp_server  # if published to PyPI

If installing from source, clone the repo and install in editable mode:

git clone https://github.com/OWNER/carlosgalisteo-catastro_mcp_server.git
cd carlosgalisteo-catastro_mcp_server
pip install -e .

3. Run the MCP server via UVX (as described in the repository):

uvx catastro_mcp_server

4. Verify the server is running by hitting its base URL/health endpoint as documented in the project (default port and routes are defined by the server configuration).

Notes:

• If you prefer to run with Docker or another environment, adapt the command accordingly (see mcp_config examples).

Tips and common issues:

• Ensure your Python environment has network access to external Catastro endpoints; some services may require stable DNS resolution.
• If you encounter SSL or certificate issues when accessing external services, verify system CA certificates or run with appropriate trust settings.
• The INSPIRE WFS CP utilities depend on GetCapabilities responses; if a capability document changes, you may need to refresh cached schemas.
• For large parcel queries, consider using the dcnp_por_rc and parcela_gml_por_rc tools in batched fashion to avoid timeouts.
• Environment variables can be used to configure endpoints, timeouts, or authentication if needed; define them in the mcp_config under env if your deployment requires overrides.