Cesium MCP

AI-Powered 3D Globe Control via Model Context Protocol

Connect any MCP-compatible AI agent to CesiumJS — camera, layers, entities, spatial analysis, all through natural language.

Website · 中文 · Getting Started · API Reference

---

Demo

demo.mp4

Packages

Package	Description	npm
cesium-mcp-bridge	Browser SDK — embeds in your CesiumJS app, receives commands via WebSocket
cesium-mcp-runtime	MCP Server (stdio + HTTP) — 58 tools (12 toolsets) + 2 resources, dynamic discovery
cesium-mcp-dev	IDE MCP Server — CesiumJS API helper for coding assistants

Architecture

flowchart LR
  subgraph clients ["AI Clients"]
    A["Claude / Cursor\nVS Code"]
    D["Dify / n8n\nRemote MCP"]
  end

  subgraph server ["cesium-mcp-runtime\n(Node.js)"]
    R["MCP Server\n58 tools · 12 toolsets"]
  end

  subgraph browser ["Browser"]
    B["cesium-mcp-bridge"]
    C["CesiumJS Viewer"]
  end

  A -- "stdio / MCP" --> R
  D -- "Streamable HTTP" --> R
  R -- "WebSocket\nJSON-RPC" --> B
  B --> C

  style clients fill:#1e293b,stroke:#528bff,color:#e2e8f0
  style server fill:#1e293b,stroke:#155EEF,color:#e2e8f0
  style browser fill:#1e293b,stroke:#12B76A,color:#e2e8f0

Loading

Quick Start

1. Install the bridge in your CesiumJS app

npm install cesium-mcp-bridge

import { CesiumBridge } from 'cesium-mcp-bridge';

const bridge = new CesiumBridge(viewer);

2. Start the MCP runtime

# stdio mode (default — for Claude Desktop, VS Code, Cursor)
npx cesium-mcp-runtime

# HTTP mode (for Dify, remote/cloud MCP clients)
npx cesium-mcp-runtime --transport http --port 3000

3. Connect your AI agent

Add to your MCP client config (e.g. Claude Desktop):

{
  "mcpServers": {
    "cesium": {
      "command": "npx",
      "args": ["-y", "cesium-mcp-runtime"]
    }
  }
}

Now ask your AI: "Fly to the Eiffel Tower and add a red marker"

58 Available Tools

Tools are organized into 12 toolsets. Default mode enables 4 core toolsets (~31 tools). Set CESIUM_TOOLSETS=all for everything, or let the AI discover and activate toolsets dynamically at runtime.

i18n: Tool descriptions default to English. Set CESIUM_LOCALE=zh-CN for Chinese.

Toolset	Tools
view (default)	flyTo, setView, getView, zoomToExtent, saveViewpoint, loadViewpoint, listViewpoints, exportScene
entity (default)	addMarker, addLabel, addModel, addPolygon, addPolyline, updateEntity, removeEntity, batchAddEntities, queryEntities, getEntityProperties
layer (default)	addGeoJsonLayer, listLayers, removeLayer, clearAll, setLayerVisibility, updateLayerStyle, getLayerSchema, setBasemap
interaction (default)	screenshot, highlight, measure
camera	lookAtTransform, startOrbit, stopOrbit, setCameraOptions
entity-ext	addBillboard, addBox, addCorridor, addCylinder, addEllipse, addRectangle, addWall
animation	createAnimation, controlAnimation, removeAnimation, listAnimations, updateAnimationPath, trackEntity, controlClock, setGlobeLighting
tiles	load3dTiles, loadTerrain, loadImageryService, loadCzml, loadKml
trajectory	playTrajectory
heatmap	addHeatmap
scene	setSceneOptions, setPostProcess
geolocation	geocode

Relationship with CesiumGS official MCP servers: The camera, entity-ext, and animation toolsets natively fuse capabilities from CesiumGS/cesium-mcp-server (Camera Server, Entity Server, Animation Server) into this project's unified bridge architecture. This means you get all official functionality plus additional tools — in a single MCP server, without running multiple processes.

Examples

See examples/minimal/ for a complete working demo.

Development

git clone https://github.com/gaopengbin/cesium-mcp.git
cd cesium-mcp
npm install
npm run build

Version Policy

Version format: {CesiumMajor}.{CesiumMinor}.{MCPPatch}

Segment	Meaning	Example
1.139	Tracks CesiumJS version — built & tested against Cesium ~1.139.0	1.139.8 → Cesium 1.139
.8	MCP patch — independent iterations for new tools, bug fixes, docs	1.139.7 → 1.139.8

When CesiumJS releases a new minor version (e.g. 1.140), we will bump accordingly: 1.140.0.

Related Projects

• mapbox-mcp — AI control for Mapbox GL JS
• openlayers-mcp — AI control for OpenLayers

Star History

License

MIT