MCP server that enables AI agents to control CesiumJS 3D globe with natural language. Supports camera flight, entity management, imagery layers, terrain, GeoJSON, trajectory playback, and interactive picking. Works with Claude Desktop, VS Code Copilot, Cursor and any MCP-compatible client.
Overview
Features
- 19 MCP Tools for full CesiumJS control via natural language
- Camera: flyTo, setView, getView, zoomToExtent
- Entities: addMarker, addLabel, highlight, removeLayer
- Layers: loadImageryService, load3dTiles, addGeoJsonLayer, addHeatmap
- Terrain: loadTerrain, setBasemap
- Interaction: screenshot, playTrajectory
- 2 Resources: scene state & entity list
Architecture
AI Agent ↔ MCP stdio ↔ cesium-mcp-runtime (Node.js) ↔ WebSocket ↔ cesium-mcp-bridge (Browser) ↔ CesiumJS Viewer
Quick Start
npm install cesium-mcp-bridgein your CesiumJS app- Add
CesiumMCPBridge.register(viewer) - Configure MCP client:
npx cesium-mcp-runtime
Links
Server Config
{
"mcpServers": {
"cesium-mcp-runtime": {
"command": "npx",
"args": [
"-y",
"cesium-mcp-runtime"
]
}
}
}