Site Intelligence

Score any coordinate for ecological and agricultural land suitability from satellite data

OtherPythonv0.1.4

Site Intelligence MCP

Score any geographic coordinate for ecological and agricultural land suitability, directly from your AI coding agent.

Analyses satellite and climate data around a point and returns a weighted suitability score with a per-metric breakdown: vegetation health, water access, precipitation, terrain, cropland proximity, urbanisation pressure, climate, and distance to infrastructure.

Built for agtech, precision agriculture, ecological field research, conservation planning, environmental consulting and apiculture.

Install

Requires a key for the Site Intelligence API on RapidAPI (free tier available).

Claude Code

claude mcp add site-intelligence \
  --env RAPIDAPI_KEY=your_key_here \
  -- uvx site-intelligence-mcp

Claude Desktop / Cursor / Windsurf

Add to your MCP config:

{
  "mcpServers": {
    "site-intelligence": {
      "command": "uvx",
      "args": ["site-intelligence-mcp"],
      "env": {
        "RAPIDAPI_KEY": "your_key_here"
      }
    }
  }
}

Usage

Ask your agent in plain language:

How suitable is 38.42, 27.14 for an apiary? Check May specifically.

Compare these three coordinates for a reforestation site and tell me which has the best water access.

Tool

site_score

ParameterTypeDefaultNotes
latfloatrequired-90 to 90
lonfloatrequired-180 to 180
radius_mint2000Analysis radius, 200-5000
monthint(none)1-12 for a seasonal view; omit for annual
detail"summary" | "full""summary""full" adds per-metric raw diagnostics

detail defaults to "summary" deliberately: tool results are spent from the model's context window, and the full diagnostic payload runs to several KB. Ask for "full" only when you need the underlying values.

Without uv

pip install site-intelligence-mcp

then use site-intelligence-mcp as the command with no args.

Configuration

VariableRequiredDefault
RAPIDAPI_KEYyes
BEELOCATE_RAPIDAPI_HOSTnosite-intelligence-api.p.rapidapi.com

Get a key from the Site Intelligence API listing.

Limits

  • Not a weather forecast and not a property-value estimate.
  • Resolution is bounded by the underlying satellite sources; very small radii will not resolve individual parcels.
  • Rate limits and quota follow your RapidAPI plan.

Licence

MIT

Installation

Source-derived launch command. Check the maintainer’s required arguments and credentials before running:

bash
uvx site-intelligence-mcp

Set up in your AI client

Merge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.

json
{
  "mcpServers": {
    "io-github-bayrakdaralper-site-intelligence-mcp": {
      "command": "uvx",
      "args": [
        "site-intelligence-mcp"
      ]
    }
  }
}

Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.

Claude Desktop setup reference

Package

site-intelligence-mcppypi

Compatible MCP Clients

Site Intelligence works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.

  • Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.
  • Cursor~/.cursor/mcp.jsonRestart Cursor for changes to take effect.
  • VS Code.vscode/mcp.jsonReload VS Code window for changes to take effect.
  • Windsurf~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect.
  • Claude Code.mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.

Learn More