Give any AI assistant expert-level knowledge of 3D and AR development.

The official Model Context Protocol server for SceneView -- the cross-platform 3D & AR SDK for Android (Jetpack Compose + Filament), iOS/macOS/visionOS (SwiftUI + RealityKit), and Web (Filament.js + WebXR).

Connect it to Claude, Cursor, Windsurf, or any MCP client. The assistant gets 26 specialized tools, 33 compilable code samples, a full API reference, and a code validator -- so it writes correct, working 3D/AR code on the first try.

Disclaimer: Generated code is provided "as is" without warranty. Always review before production use. See TERMS.md and PRIVACY.md.

Starting with v4.0.0-beta.1, sceneview-mcp is a lite stdio package: free tools run locally (no network round-trip) and Pro tools are transparently forwarded to the hosted gateway at https://sceneview-mcp.mcp-tools-lab.workers.dev/mcp.

Pricing (subscribe at https://sceneview-mcp.mcp-tools-lab.workers.dev/pricing):

After subscribing, you'll receive a sv_live_… API key. Set it via the SCENEVIEW_API_KEY env var in your MCP client config (see snippets below) to unlock Pro tools.

⭐ Sponsor on GitHub — help keep the free tier free.

One command -- no install required:

npx sceneview-mcp

On startup you'll see a [sceneview-mcp] v4.0.1 — LITE (free tools only) banner on stderr. Set SCENEVIEW_API_KEY to flip into HOSTED mode.

Anonymous telemetry is enabled on the free tier (MCP client name/version and tool names — no personal data, no prompt content). Opt out with SCENEVIEW_TELEMETRY=0. See PRIVACY.md for the full payload shape.

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

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

Restart Claude Desktop after saving.

claude mcp add sceneview -- npx -y sceneview-mcp

Open Settings > MCP, add a new server named sceneview with command npx -y sceneview-mcp. Or add to .cursor/mcp.json:

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

Same JSON config as above. The server communicates via stdio using the standard MCP protocol.

Generated SceneView code is only useful if it points at an asset that actually exists. search_models queries Sketchfab's public search API and returns a shortlist with names, authors, licenses, thumbnails, triangle counts, and viewer/embed URLs that the assistant can drop straight into rememberModelInstance(modelLoader, ...) or embed as a live preview.

Bring your own key (BYOK). SceneView never proxies the request — you keep the rate limit and the cost stays at zero. To set it up:

1. Create a free account at sketchfab.com/register
2. Copy your API token from sketchfab.com/settings/password
3. Set SKETCHFAB_API_KEY in your MCP client config:

{
  "mcpServers": {
    "sceneview": {
      "command": "npx",
      "args": ["-y", "sceneview-mcp"],
      "env": { "SKETCHFAB_API_KEY": "YOUR_TOKEN_HERE" }
    }
  }
}

Call it like search_models({ query: "red sports car", category: "cars-vehicles", maxResults: 6 }). If the key is missing, the tool returns a clear message explaining how to get one instead of failing silently.

Because the MCP server runs on the user's machine, analyze_project can read their project files directly. Given a path (default: process.cwd()), it:

• Detects the project type by looking for build.gradle(.kts) with io.github.sceneview:sceneview (Android), Package.swift with SceneViewSwift (iOS), or package.json with sceneview-web (Web).
• Extracts the SceneView dependency version and compares it against the latest release known to this MCP build, flagging outdated projects.
• Walks up to 30 source files (.kt, .kts, .swift, .js, .ts) and up to 500 KB total, scanning for well-known anti-patterns: Filament/ModelLoader calls inside background coroutines, the LightNode(...) { ... } trailing-lambda bug, deprecated 2.x APIs (ArSceneView, TransformableNode, PlacementNode, ViewRenderable, loadModelAsync), and com.google.ar.sceneform.* imports.
• Returns a structured { projectType, sceneViewVersion, latestVersion, isOutdated, warnings, suggestions } report, plus a Markdown summary.

The tool is read-only, never writes to disk, and gracefully handles missing directories. Use it when the user asks "is my project up to date?" or as a quick sanity check before generating new code for an existing codebase.

The assistant calls get_ar_setup + get_sample("ar-model-viewer") and returns a complete, compilable Kotlin composable with all imports, Gradle dependencies, and manifest entries. Ready to paste into Android Studio.

The assistant calls get_ios_setup("3d") + get_sample("ios-model-viewer") and returns Swift code with the SPM dependency, Info.plist entries, and a working SwiftUI view.

The assistant calls get_node_reference("LightNode") and returns the exact function signature, parameter types, defaults, and a usage example -- including the critical detail that apply is a named parameter, not a trailing lambda.

The assistant calls validate_code with the generated snippet and checks it against 15+ rules: threading violations, null safety, API correctness, lifecycle issues, deprecated APIs. Problems are flagged with explanations before the code reaches the user.

The assistant calls render_3d_preview and returns an interactive link to a browser-based 3D viewer with orbit controls and optional AR mode.

Without this MCP server, AI assistants regularly:

• Recommend deprecated Sceneform (abandoned 2021) instead of SceneView
• Generate imperative View-based code instead of Jetpack Compose
• Use wrong API signatures or outdated parameter names
• Miss the LightNode named-parameter gotcha (apply = not trailing lambda)
• Forget null-checks on rememberModelInstance (it returns null while loading)
• Have no knowledge of SceneView's iOS/Swift API at all

With this MCP server, AI assistants:

• Always use the current SceneView 4.0.0 API surface
• Generate correct Compose-native 3D/AR code for Android
• Generate correct SwiftUI-native code for iOS/macOS/visionOS
• Know about all 35+ node types and their exact parameters
• Validate code against 15+ rules before presenting it
• Provide working, tested sample code for 33 scenarios

The MCP server is tested with 2360 unit tests across 98 test suites covering:

• Every tool response (correct output, error handling, edge cases)
• All 33 code samples (compilable structure, correct imports, no deprecated APIs)
• Code validator rules (true positives and false-positive resistance)
• Node reference parsing (all 26+ types extracted correctly from llms.txt)
• Resource responses (API reference, GitHub issues integration)

 Test Files  22 passed (22)
      Tests  2360 passed (2360)
   Duration  624ms

All tools work fully offline except sceneview://known-issues (GitHub API, cached 10 min).

1. Ensure Node.js 18+ is installed: node --version
2. Test manually: npx sceneview-mcp -- should start without errors
3. Restart your AI client after changing the MCP configuration

Install Node.js from nodejs.org (LTS recommended). npm and npx are included.

• Claude Desktop: check the MCP icon in the input bar -- it should show "sceneview" as connected
• Cursor: check Settings > MCP for green status
• Restart the AI client to force a reconnect

The only network call is to the GitHub API (for known issues). All other tools work offline. For corporate proxies:

{
  "mcpServers": {
    "sceneview": {
      "command": "npx",
      "args": ["-y", "sceneview-mcp"],
      "env": {
        "HTTPS_PROXY": "http://proxy.example.com:8080"
      }
    }
  }
}

cd mcp
npm install
npm run prepare  # Copy llms.txt + build TypeScript
npm test         # 2360 tests
npm run dev      # Start with tsx (hot reload)

mcp/
  src/
    index.ts          # MCP server entry point (26 tools, 2 resources)
    samples.ts         # 33 compilable code samples (Kotlin + Swift)
    validator.ts       # Code validator (15+ rules, Kotlin + Swift)
    node-reference.ts  # Node type parser (extracts from llms.txt)
    guides.ts          # Best practices, AR setup, roadmap, troubleshooting
    migration.ts       # v2 -> v3 migration guide
    preview.ts         # 3D preview URL generator
    artifact.ts        # HTML artifact generator (model-viewer, charts, product 360)
    issues.ts          # GitHub issues fetcher (cached)
  llms.txt             # Bundled API reference (copied from repo root)

1. Fork the repository
2. Create a feature branch
3. Add tests for new tools or rules
4. Run npm test -- all 2360+ tests must pass
5. Submit a pull request

See CONTRIBUTING.md for the full guide.

• LICENSE -- MIT License
• TERMS.md -- Terms of Service
• PRIVACY.md -- Privacy Policy (no data collected)