io.github.gaopengbin/cesium-mcp-runtime MCP Server
io.github.gaopengbin/cesium-mcp-runtime
Control CesiumJS 3D globes with AI commands via MCP—camera, layers, entities, animation, and interaction.
What is the io.github.gaopengbin/cesium-mcp-runtime MCP server?
The Cesium MCP Runtime is an MCP server that exposes 62 AI-controllable commands for CesiumJS 3D globes. It enables Claude, Cursor, and other MCP clients to programmatically manage camera views, add/update entities, control layers, animate scenes, and interact with geospatial data through a unified command interface.
This server bridges CesiumJS 3D mapping to AI agents, letting you fly to locations, add markers and models, manage layers, create animations, and capture screenshots—all via natural language commands in Claude Desktop, Cursor, or Dify. It supports multiple integration paths: browser-only agents, WebMCP (Chrome 149+), function calling in web apps, or MCP runtime for desktop clients.
How to install io.github.gaopengbin/cesium-mcp-runtime
Copy-paste configuration for popular MCP clients.
Tools & capabilities
Tools this server exposes to the agent.
flyTo— Navigate the camera to a specified location or entitysetView— Set the camera view to a specific position and orientationgetView— Retrieve the current camera view statezoomToExtent— Zoom the camera to fit a geographic extentsaveViewpoint— Save the current camera viewpoint for later recallloadViewpoint— Load and restore a previously saved viewpointlistViewpoints— List all saved viewpointsexportScene— Export the current scene as an image or dataaddMarker— Add a point marker to the mapaddLabel— Add a text label to the mapaddModel— Add a 3D model to the sceneaddPolygon— Add a polygon shape to the mapaddPolyline— Add a line or polyline to the mapupdateEntity— Modify properties of an existing entityremoveEntity— Delete an entity from the scenebatchAddEntities— Add multiple entities at oncequeryEntities— Search for entities by properties or locationgetEntityProperties— Retrieve detailed properties of an entityaddGeoJsonLayer— Load and display GeoJSON data as a layeraddGeoJsonPrimitive— Add GeoJSON data as primitives
Use cases
- Fly to and visualize geographic locations with natural language commands like 'Show me the Eiffel Tower'
- Add and manage 3D markers, models, and labels on a Cesium globe for data visualization
- Create animated camera tours and entity trajectories for presentations or storytelling
- Load and display geospatial data formats (GeoJSON, KML, CZML, 3D Tiles) via AI commands
- Measure distances and areas, capture screenshots, and export scenes programmatically
io.github.gaopengbin/cesium-mcp-runtime MCP server FAQ
It's an MCP server that exposes 62 commands for controlling CesiumJS 3D globes. You can use it with Claude Desktop, Cursor, or Dify to programmatically manage camera views, add entities, control layers, animate scenes, and interact with geospatial data.
Yes. The server itself is MIT-licensed and free. CesiumJS is open-source. Some features (like Cesium Ion imagery services) may require a free or paid Cesium Ion account, but the core MCP runtime has no cost.
Install via npm: `npx cesium-mcp-runtime`. Then add it to your MCP client config (Claude Desktop or Cursor) with the command `npx cesium-mcp-runtime`. See the README for exact config syntax.
No, not required for basic use. The server works with open-source CesiumJS. If you want to use Cesium Ion imagery services, you can set a token via the `setIonToken` tool or environment variable.
Browser Agent (simplest, no backend), WebMCP (Chrome 149+, page-local tools), function calling (embed in your web app), or MCP runtime (Claude Desktop/Cursor/Dify). Pick based on your deployment scenario.
Yes. Install `cesium-mcp-bridge` and call its tools directly via function calling, or use the MCP runtime as a separate server that your app communicates with.
README (reference)
Source of truth, from the repository.
Demo
https://github.com/user-attachments/assets/8a40565a-fcdd-47bf-ae67-bc870611c908
Packages & Entry Points
| Module | Role | Status | Links |
|---|---|---|---|
| cesium-mcp-contracts | Transport-neutral names, descriptions, and JSON Schemas for browser tools | New shared layer | source |
| cesium-mcp-bridge | Protocol- and transport-free Cesium command executor (60+ commands) | Mainline, actively iterated | |
| cesium-mcp-webmcp | Native document.modelContext adapter for Cesium tool contracts | New browser adapter | source |
| examples/webmcp-integration | Focused npm + Vite integration without a chat UI or MCP server | Developer example | example |
| examples/browser-agent | Browser-only AI agent with automatic WebMCP exposure | Recommended | example · live demo |
| cesium-mcp-runtime | MCP server (stdio + HTTP) | Stable MCP SDK v2 | |
| cesium-mcp-dev | CesiumJS API knowledge base for coding assistants | Maintained |
Which one? Personal project or quick try → browser-agent. Let a compatible browser agent discover page-local Cesium tools → WebMCP. Existing web app embedding an AI assistant → bridge + your own function calling. Calling from Claude Desktop / Cursor / Dify → MCP runtime.
Architecture
flowchart LR
subgraph clients ["AI Drivers (pick one)"]
BA["Browser Agent\n(in the same page)"]
WM["WebMCP Agent\n(browser-provided)"]
FC["Your web app\nfunction calling"]
MCP["Claude / Cursor / Dify\nvia MCP runtime"]
end
CONTRACTS["cesium-mcp-contracts\ntool definitions"]
WEBMCP["cesium-mcp-webmcp\nnative adapter"]
subgraph core ["cesium-mcp-bridge (browser)"]
B["60+ tools\nprotocol-agnostic dispatcher"]
C["CesiumJS Viewer"]
end
CONTRACTS -.-> BA
CONTRACTS -.-> WEBMCP
BA -- "in-page call" --> B
WM -- "document.modelContext" --> WEBMCP
WEBMCP --> B
FC -- "in-page call" --> B
MCP -- "WebSocket / JSON-RPC" --> B
B --> C
style clients fill:#1e293b,stroke:#528bff,color:#e2e8f0
style core fill:#1e293b,stroke:#12B76A,color:#e2e8f0
The bridge remains the execution core, while contracts and protocol adapters stay separate. Pick whichever driver matches your scenario — they all reach the same Cesium command layer. On WebMCP-capable browsers, cesium-mcp-webmcp can expose 61 browser-safe commands in 12 selectable toolsets through document.modelContext without adding an MCP transport or backend server.
Quick Start
Path 0 — Try in 30 seconds (browser agent, recommended)
Open the live demo and ask—the hosted model is ready without a browser API key:
"Fly to the Eiffel Tower and drop a red marker"
Fork the examples/browser-agent folder to deploy your own.
Path 1 — Expose Cesium tools through WebMCP (Chrome 149+ experimental)
The browser-agent example automatically registers all 61 browser-safe page tools when document.modelContext is available. Its built-in chat uses automatic toolset routing to keep each normal request at 20 tools or fewer, while still offering explicit core, single-toolset, and all-61 modes:
npm run build -w packages/cesium-mcp-bridge
npm run build -w packages/cesium-mcp-webmcp
npx serve . -l 4173
Open http://localhost:4173/examples/browser-agent/, click Start, then inspect or execute the tools in DevTools → Application → WebMCP. Enable #enable-webmcp-testing and #devtools-webmcp-support in chrome://flags for local testing.
Application developers install the adapter separately. End users only open the integrated website; they do not install npm packages or run an MCP server.
npm install cesium cesium-mcp-bridge cesium-mcp-webmcp
import { CesiumBridge } from 'cesium-mcp-bridge'
import { registerCesiumWebMcp } from 'cesium-mcp-webmcp'
const bridge = new CesiumBridge(viewer)
const registration = await registerCesiumWebMcp(bridge, {
toolsets: 'all',
excludeTools: ['geocode'], // add your own browser geocoder to expose this tool
})
// Later, if the page is unmounted:
registration.unregister()
See the WebMCP adapter API for custom integrations. For a complete npm + Vite application, start from the WebMCP integration example.
Path 2 — Embed in your own web app (function calling)
npm install cesium-mcp-bridge
import { CesiumBridge } from 'cesium-mcp-bridge';
const bridge = new CesiumBridge(viewer);
// Then: send the bridge's tool schema to any LLM that supports function/tool calling,
// route the model's tool calls to bridge.execute(name, params).
See examples/browser-agent/index.html for a complete loop with OpenAI-compatible APIs.
Path 3 — Use from Claude Desktop / Cursor / Dify (MCP)
Install bridge as in Path 2, then start the MCP runtime:
# Stable channel — npm latest, MCP SDK v2
npx cesium-mcp-runtime
# HTTP mode
npx cesium-mcp-runtime --transport http --port 3000
The stable release serves existing MCP 2025-11-25 clients and the new
2026-07-28 protocol from the same stdio/HTTP entry. It uses the stable
TypeScript SDK v2 and passes the official server-stateless conformance
scenario (28/28).
MCP client config:
{
"mcpServers": {
"cesium": {
"command": "npx",
"args": ["-y", "cesium-mcp-runtime"]
}
}
}
62 Available Command Tools
Tools are organized into 12 toolsets. Default mode enables 4 core toolsets (30 tools). Set CESIUM_TOOLSETS=all for everything, or let the AI discover and activate toolsets dynamically at runtime.
Canonical contracts: Tool descriptions default to English; set
CESIUM_LOCALE=zh-CNfor Chinese. Titles, behavior annotations, localized descriptions, defaults, input validation, MCP output schemas, and structured results all come from the shared JSON Schemas incesium-mcp-contracts. Textcontentremains available for older clients.
| 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, addGeoJsonPrimitive, 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, load3dGaussianSplat, loadTerrain, loadImageryService, loadCzml, loadKml, setEdgeDisplayMode |
| trajectory | playTrajectory |
| heatmap | addHeatmap |
| scene | setSceneOptions, setPostProcess, setIonToken (Runtime only) |
| geolocation | geocode |
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
npm test
npm run test:contracts
npm run test:routing
npm run test:e2e:packed
test:contracts is the focused parity gate for MCP Runtime metadata, WebMCP registration, Function Calling definitions, and the 60-tool Bridge Executor Registry.
test:routing evaluates bilingual and multi-intent Browser Agent requests across all 12 toolsets, checking required-tool recall and the 20-tool automatic-routing budget.
test:e2e:packed builds npm tarballs, installs them in a clean temporary project, opens the real Cesium Viewer, and verifies a Runtime-WebSocket-Bridge command round trip.
Version Policy
Version format: {CesiumMajor}.{CesiumMinor}.{MCPPatch}
| Segment | Meaning | Example |
|---|---|---|
1.143 | Tracks CesiumJS version — built & tested against Cesium ~1.143.0 | 1.143.0 → Cesium 1.143 |
.x | MCP patch — independent iterations for new tools, bug fixes, docs | 1.143.0 → 1.143.1 |
Official CesiumJS releases are reviewed before the compatibility baseline is bumped; the project does not automatically claim support for a newer release without Bridge verification.
Related Projects
- mapbox-mcp — AI control for Mapbox GL JS
- openlayers-mcp — AI control for OpenLayers
Star History
License
Related MCP servers
AI-powered CesiumJS development tools with 60+ commands for Claude, Cursor, and browser agents.

useVyre Context
useVyre component context for AI agents — valid props, variants, anti-patterns, and design tokens.

Aguara MCP
Scan skills, MCP configs, and agent content for injection and supply-chain risks. Offline, no LLM.

AI Skill Store
Agent-first skill marketplace with USK open standard for Claude, Cursor, Gemini, Codex CLI.
CNCF release intelligence: typed changes from release notes; check_stack compares versions locally.

