Cesium MCP connects any MCP-compatible AI agent to CesiumJS, allowing control of camera, layers, entities, and spatial analysis through natural language.
From the registry: AI-powered 3D globe control via MCP. Camera, layers, markers, spatial analysis with CesiumJS.
$ npm install cesium-mcp-bridgehttps://www.npmjs.com/package/cesium-mcp-bridgePlease install the `cesium-mcp-runtime` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install cesium-mcp-bridge in your CesiumJS app** — Embed the bridge SDK in your browser CesiumJS app to receive commands Run: `npm install cesium-mcp-bridge` (https://www.npmjs.com/package/cesium-mcp-bridge)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","cesium-mcp-runtime"]
- optional environment variables:
- `CESIUM_TOOLSETS`: Set to 'all' to enable all toolsets, otherwise default 4 core toolsets (example: `all`)
- `CESIUM_LOCALE`: Set to 'zh-CN' for Chinese tool descriptions (example: `zh-CN`)
Note: 58 tools, 12 toolsets for AI control of CesiumJS via WebSocket bridge. Also supports HTTP transport: `npx cesium-mcp-runtime --transport http --port 3000`.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CESIUM_TOOLSETSSet to 'all' to enable all toolsets or let the AI discover and activate toolsets dynamically.CESIUM_LOCALESet to 'zh-CN' for Chinese tool descriptions.