An MCP for retrieving land use data for a given location
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"landuse-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# landuse-mcp A Model Context Protocol (MCP) server for retrieving land use data for given geographical locations using the National Land Cover Database (NLCD) and other geospatial datasets. ## Features - **Land Cover Data**: Retrieve detailed land cover classifications for any coordinate - **Soil Type Information**: Get FAO soil type classifications for geographical points - **Temporal Data**: Access available dates for land use data at specific locations - **MCP Integration**: Full Model Context Protocol support for AI agents - **Geospatial Processing**: Built on robust geospatial libraries for accurate data retrieval ## Quick Start ```bash # Install dependencies and set up development environment make dev # Run the MCP server make server # Run tests make test-coverage # Demo functionality make demo ``` ## Installation ### From PyPI (Recommended) ```bash # Install with uvx uvx landuse-mcp ``` ### From Source ```bash # Clone the repository git clone https://github.com/justaddcoffee/landuse-mcp.git cd landuse-mcp # Install in development mode make dev ``` ## Usage ### Command Line Interface ```bash # Run the MCP server landuse-mcp # Or using uv uv run landuse-mcp ``` ### Python API ```python from landuse_mcp.main import get_land_cover, get_soil_type, get_landuse_dates # Get land cover data for Death Valley land_cover = get_land_cover(36.5322649, -116.9325408, "2001-01-01", "2002-01-01") print(land_cover) # Get soil type for a location soil_type = get_soil_type(32.95047, -87.393259) print(soil_type) # e.g., "Cambisols" # Get available dates for land use data dates = get_landuse_dates(36.5322649, -116.9325408) print(dates) # List of available dates ``` ### Testing MCP Protocol ```bash # Test MCP handshake make test-mcp # Extended MCP testing make test-mcp-extended ``` ## Integration with AI Tools ### Claude Desktop Add this to your Claude Desktop configuration file (`~/Library/Application Support/Claude/claude_desktop_config.json`): ``…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.