cesium-mcp
AI-powered 3D globe control via Model Context Protocol. Connect any MCP-compatible AI agent to CesiumJS — camera, layers, entities, spatial analysis through 19 natural language tools.
README
<div align="center"> <img src="docs/public/logo.svg" alt="Cesium MCP" width="120">
<h1>Cesium MCP</h1>
<p><strong>AI-Powered 3D Globe Control via Model Context Protocol</strong></p>
<p>Connect any MCP-compatible AI agent to <a href="https://cesium.com/">CesiumJS</a> — camera, layers, entities, spatial analysis, all through natural language.</p>
<p> <a href="https://gaopengbin.github.io/cesium-mcp/">Website</a> · <a href="README.zh-CN.md">中文</a> · <a href="https://gaopengbin.github.io/cesium-mcp/guide/getting-started.html">Getting Started</a> · <a href="https://gaopengbin.github.io/cesium-mcp/api/bridge.html">API Reference</a> </p>
<p> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="License: MIT"></a> <a href="https://github.com/gaopengbin/cesium-mcp/actions/workflows/ci.yml"><img src="https://github.com/gaopengbin/cesium-mcp/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <a href="https://www.npmjs.com/package/cesium-mcp-bridge"><img src="https://img.shields.io/npm/v/cesium-mcp-bridge?label=bridge" alt="npm bridge"></a> <a href="https://www.npmjs.com/package/cesium-mcp-runtime"><img src="https://img.shields.io/npm/v/cesium-mcp-runtime?label=runtime" alt="npm runtime"></a> <a href="https://www.npmjs.com/package/cesium-mcp-dev"><img src="https://img.shields.io/npm/v/cesium-mcp-dev?label=dev" alt="npm dev"></a> <a href="https://glama.ai/mcp/servers/gaopengbin/cesium-mcp"><img src="https://glama.ai/mcp/servers/gaopengbin/cesium-mcp/badges/card.svg" alt="cesium-mcp MCP server"></a> </p> </div>
Demo
https://github.com/user-attachments/assets/8a40565a-fcdd-47bf-ae67-bc870611c908
Packages
| Package | Description | npm |
|---|---|---|
| cesium-mcp-bridge | Browser SDK — embeds in your CesiumJS app, receives commands via WebSocket | |
| cesium-mcp-runtime | MCP Server (stdio) — 43 tools (10 toolsets) + 2 resources, dynamic discovery | |
| cesium-mcp-dev | IDE MCP Server — CesiumJS API helper for coding assistants |
Architecture
┌──────────────┐ stdio ┌──────────────────┐ WebSocket ┌──────────────────┐
│ AI Agent │ ◄────────► │ cesium-mcp- │ ◄─────────► │ cesium-mcp- │
│ (Claude, │ MCP │ runtime │ JSON-RPC │ bridge │
│ Cursor…) │ │ (Node.js) │ │ (Browser) │
└──────────────┘ └──────────────────┘ └──────────────────┘
│
┌──────▼──────┐
│ CesiumJS │
│ Viewer │
└─────────────┘
Quick Start
1. Install the bridge in your CesiumJS app
npm install cesium-mcp-bridge
import { CesiumMcpBridge } from 'cesium-mcp-bridge';
const bridge = new CesiumMcpBridge(viewer, { port: 9100 });
bridge.connect();
2. Start the MCP runtime
npx cesium-mcp-runtime
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"
43 Available Tools
Tools are organized into 10 toolsets. Default mode enables 4 core toolsets (~19 tools). Set CESIUM_TOOLSETS=all for everything, or let the AI discover and activate toolsets dynamically at runtime.
| Toolset | Tools |
|---|---|
| view (default) | flyTo, setView, getView, zoomToExtent |
| entity (default) | addMarker, addLabel, addModel, addPolygon, addPolyline, updateEntity, removeEntity |
| layer (default) | addGeoJsonLayer, listLayers, removeLayer, setLayerVisibility, updateLayerStyle, setBasemap |
| interaction (default) | screenshot, highlight |
| 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 |
| trajectory | playTrajectory |
| heatmap | addHeatmap |
Relationship with CesiumGS official MCP servers: The
camera,entity-ext, andanimationtoolsets 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
The major.minor version tracks CesiumJS (e.g. 1.139.x targets Cesium ~1.139.0). Patch versions are independent for MCP feature iterations.
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。