Cesium AI Integrations
Cesium AI Integrations is a collection of reference integrations and experiments connecting the Cesium ecosystem with AI systems including Model Context Protocol (MCP) tools, retrieval pipelines, and agent skills.
What is Cesium AI Integrations?
Cesium AI Integrations is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to cesium ai integrations is a collection of reference integrations and experiments connecting the cesium ecosystem with ai systems including model context protocol (mcp) tools, retrieval pipelines, and ...
Cesium AI Integrations is a collection of reference integrations and experiments connecting the Cesium ecosystem with AI systems including Model Context Protocol (MCP) tools, retrieval pipelines, and agent skills.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Cesium AI Integrations is a collection of reference integrat
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx cesium-ai-integrationsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Cesium AI Integrations
Cesium AI Integrations is an official collection of reference integrations from Cesium GS that connects the CesiumJS 3D geospatial visualization ecosystem with AI systems via the Model Context Protocol. It provides separate MCP servers for distinct CesiumJS concerns — camera control, entity management, animation, imagery layers, terrain, and 3D Tiles — plus a gateway server that aggregates them. AI agents connected to these servers can programmatically fly cameras to locations, place 3D entities (points, polygons, models), control globe lighting and animations, manage imagery providers, and query geolocation data, enabling the creation of AI-driven geospatial applications and intelligent 3D map interfaces.
Prerequisites
- Node.js 22 or later (required for native WebSocket support)
- pnpm 8 or later for package management
- A running CesiumJS application in a browser that the MCP servers can connect to via WebSocket or SSE
- An MCP-compatible client such as Claude Desktop or Claude Code
- A Cesium Ion account and access token if using Ion-hosted 3D Tiles or terrain assets
Clone the repository
Clone the cesium-ai-integrations repository and navigate into the MCP directory.
git clone https://github.com/CesiumGS/cesium-ai-integrations.git
cd cesium-ai-integrations/mcp/cesium-jsInstall dependencies and build all servers
Install all packages using pnpm and build the TypeScript source for all MCP servers in the monorepo.
pnpm install
pnpm run buildConfigure environment variables for the servers
Set port and protocol environment variables. Each server listens on its own port. WebSocket is the preferred communication protocol between the MCP servers and your CesiumJS browser app.
# Optional overrides (defaults shown)
export CAMERA_SERVER_PORT=3002
export ENTITY_SERVER_PORT=3003
export ANIMATION_SERVER_PORT=3004
export IMAGERY_SERVER_PORT=3005
export TILES_SERVER_PORT=3006
export TERRAIN_SERVER_PORT=3007
export GATEWAY_SERVER_PORT=3010
export COMMUNICATION_PROTOCOL=websocketAdd the servers to your MCP client configuration
Register one or more CesiumJS MCP servers in your Claude Desktop config. Start with the gateway server to get access to all domains, or add individual servers for focused capabilities.
{
"mcpServers": {
"cesium-camera": {
"command": "node",
"args": ["PATH_TO_REPO/mcp/cesium-js/servers/camera-server/build/index.js"],
"env": {
"COMMUNICATION_PROTOCOL": "websocket",
"CAMERA_SERVER_PORT": "3002",
"STRICT_PORT": "false"
}
},
"cesium-gateway": {
"command": "node",
"args": ["PATH_TO_REPO/mcp/cesium-js/servers/gateway-server/build/index.js"],
"env": {
"COMMUNICATION_PROTOCOL": "websocket",
"GATEWAY_SERVER_PORT": "3010"
}
}
}
}Connect your CesiumJS application
In your CesiumJS browser application, add the provided client-side connector library that opens a WebSocket (or SSE) connection back to the running MCP servers. Follow the cesium-js README for the exact client integration code.
Test with a camera fly-to command
Ask Claude to fly the camera to a geographic location. The camera server will relay the fly_to command over WebSocket to your CesiumJS viewer.
Cesium AI Integrations Examples
Client configuration
Claude Desktop config for the Cesium camera server. Replace PATH_TO_REPO with the absolute path to your cloned repository.
{
"mcpServers": {
"cesium-camera": {
"command": "node",
"args": ["/Users/yourname/cesium-ai-integrations/mcp/cesium-js/servers/camera-server/build/index.js"],
"env": {
"COMMUNICATION_PROTOCOL": "websocket",
"CAMERA_SERVER_PORT": "3002",
"STRICT_PORT": "false"
}
}
}
}Prompts to try
Once connected to a live CesiumJS application, use these prompts with Claude to control the 3D globe.
- "Fly the camera to Mount Everest at an altitude of 10,000 meters"
- "Add a red point entity at longitude -74.006, latitude 40.7128 with the label 'New York'"
- "Load the Cesium World Terrain from Ion and set it as the active terrain provider"
- "Add an OpenStreetMap imagery layer to the globe"
- "Start an orbit animation around the current camera position with a radius of 5000 meters"
- "List all 3D Tile tilesets currently loaded in the viewer"Troubleshooting Cesium AI Integrations
MCP server starts but the CesiumJS app does not receive commands
Verify that COMMUNICATION_PROTOCOL is set to 'websocket' and that the browser app's client connector is pointing to the correct server port (e.g., ws://localhost:3002). Check browser console for WebSocket connection errors.
Port conflict: server fails to bind to the default port
Set STRICT_PORT=false to allow the server to fall back to any available port, or explicitly set a free port via the appropriate _SERVER_PORT environment variable.
Node.js version error about native WebSocket not being available
The cesium-js servers require Node.js 22 or later for the native WebSocket API. Run node --version to check, and upgrade via nvm: nvm install 22 && nvm use 22.
Frequently Asked Questions about Cesium AI Integrations
What is Cesium AI Integrations?
Cesium AI Integrations is a Model Context Protocol (MCP) server that cesium ai integrations is a collection of reference integrations and experiments connecting the cesium ecosystem with ai systems including model context protocol (mcp) tools, retrieval pipelines, and agent skills. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Cesium AI Integrations?
Follow the installation instructions on the Cesium AI Integrations GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Cesium AI Integrations?
Cesium AI Integrations works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Cesium AI Integrations free to use?
Yes, Cesium AI Integrations is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Cesium AI Integrations Alternatives — Similar Cloud Services Servers
Looking for alternatives to Cesium AI Integrations? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Cesium AI Integrations in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Cesium AI Integrations?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.