PluginBench
MCP Server
Active
Apache-2.0

io.github.ThomasGorisse/sceneview MCP Server

io.github.ThomasGorisse/sceneview

What is the io.github.ThomasGorisse/sceneview MCP server?

The SceneView MCP server (io.github.ThomasGorisse/sceneview) is an MCP integration for the SceneView 3D/AR SDK that gives AI coding assistants like Claude access to SceneView's API documentation, samples, validation, and code generation for building 3D and AR apps. It targets Android, iOS, Web, Desktop, TV, Flutter, and React Native, all built on the same Compose-native SceneView concepts (nodes, ARCore/RealityKit/Filament rendering).</parameter> <parameter name="overview">SceneView is a 3D & AR SDK that provides a Compose-native (and SwiftUI/JS-native) way to build 3D and AR experiences across Android, iOS/macOS/visionOS, Web, Desktop, TV, Flutter, and React Native — using Filament and RealityKit for rendering and ARCore for AR tracking. The SceneView MCP server exposes this SDK's documentation, samples, code validation, and code generation to AI agents so tools like Claude can scaffold and write correct SceneView code (e.g., AR scenes with tap-to-place models, 3D node graphs, animations, physics) without the developer needing to look up API references manually.</parameter> <parameter name="tagline">Bring SceneView's 3D & AR API docs, samples, and code generation directly into your AI coding assistant.

How to install io.github.ThomasGorisse/sceneview

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "sceneview": {
      "command": "npx",
      "args": [
        "-y",
        "sceneview-mcp"
      ]
    }
  }
}
Cursor
~/.cursor/mcp.json
{
  "mcpServers": {
    "sceneview": {
      "command": "npx",
      "args": [
        "-y",
        "sceneview-mcp"
      ]
    }
  }
}
Windsurf
~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "sceneview": {
      "command": "npx",
      "args": [
        "-y",
        "sceneview-mcp"
      ]
    }
  }
}
VS Code
.vscode/mcp.json
{
  "servers": {
    "sceneview": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "sceneview-mcp"
      ]
    }
  }
}
Claude Code
claude mcp add sceneview -- npx -y sceneview-mcp

Use cases

  • Ask Claude to scaffold an AR app with tap-to-place 3D models using ARCore/RealityKit
  • Generate SceneView node code (models, primitives, lighting, physics) for Android, iOS, or Web
  • Look up SceneView API docs and sample code for a given node type or capability directly from the AI assistant
  • Validate generated SceneView/Compose or SwiftUI 3D scene code against the SDK's API
  • Migrate existing Sceneform-based Android AR code to SceneView with AI assistance

io.github.ThomasGorisse/sceneview MCP server FAQ

What does the SceneView MCP server do?

It connects AI coding assistants (like Claude) to the SceneView 3D/AR SDK, providing API documentation, sample code, code validation, and code generation so the AI can help build 3D and AR apps for Android, iOS, Web, Desktop, TV, Flutter, and React Native.

Is the SceneView MCP server free?

The README does not state pricing; it is distributed as an npm package (sceneview-mcp) installable via npx, and the underlying SceneView SDK is an open-source project on GitHub.

How do I install it in Claude Code or Claude Desktop?

Run `claude mcp add sceneview -- npx sceneview-mcp`, or add it manually via JSON config: `{ "mcpServers": { "sceneview": { "command": "npx", "args": ["-y", "sceneview-mcp"] } } }`.

Does it require authentication?

No authentication is mentioned in the README; it runs locally via npx as a standard MCP server.

Can I use it with Cursor?

The README only documents Claude Code/Claude Desktop installation via `npx sceneview-mcp`, but since it's a standard npm-distributed MCP server, it can likely be added to any MCP-compatible client (like Cursor) using the same command/args configuration.

What platforms does the underlying SceneView SDK support?

SceneView supports Android (3D + AR), iOS/macOS/visionOS, Web, Desktop, Android TV, Flutter, and React Native, all sharing the same node-based 3D/AR concepts.

README (reference)

Source of truth, from the repository.

SceneView

3D & AR for every platform.

Build 3D and AR experiences with the UI frameworks you already know. Same concepts, same simplicity — Android, iOS, Web, Desktop, TV, Flutter, React Native.

<!-- Platforms -->

Android 3D Android AR iOS / macOS / visionOS sceneview.js MCP Server Flutter React Native

<!-- Status -->

CI License GitHub Stars GitHub Release Discord Sponsors Open Collective

Try the demo apps

See SceneView capabilities in action — install the live demos in one tap:

<p> <a href="https://play.google.com/store/apps/details?id=io.github.sceneview.demo"><img src="website-static/assets/brand/stores/google-play-badge-trimmed.png" alt="Get it on Google Play" height="56"></a>&nbsp; <a href="https://apps.apple.com/us/app/sceneview/id6761329763"><img src="website-static/assets/brand/stores/app-store.svg" alt="Download on the App Store" height="56"></a>&nbsp; <a href="https://sceneview.github.io/playground.html"><img src="website-static/assets/brand/stores/web-playground.svg" alt="Open the Web Playground" height="56"></a> </p>

Browse all sample sources in samples/ — Android · iOS · Web · Desktop · TV · Flutter · React Native.

Tip — every demo opens directly via https://sceneview.github.io/open?demo=<id>. For example, …/open?demo=ar-rerun lands straight on the AR Rerun debug screen with a single tap from any QR code or link.


Quick look

// Android — Jetpack Compose
SceneView(modifier = Modifier.fillMaxSize()) {
    rememberModelInstance(modelLoader, "models/helmet.glb")?.let {
        ModelNode(modelInstance = it, scaleToUnits = 1.0f, autoAnimate = true)
    }
}
// iOS — SwiftUI
SceneView(environment: .studio) {
    ModelNode(named: "helmet.usdz")
        .scaleToUnits(1.0)
}
<!-- Web — friendly DSL (Filament.js engine + SceneView wrapper) -->
<script src="https://cdn.jsdelivr.net/gh/sceneview/sceneview@v4.18.0/website-static/js/filament/filament.js"></script>
<script src="https://cdn.jsdelivr.net/gh/sceneview/sceneview@v4.18.0/website-static/js/sceneview.js"></script>
<script> SceneView.modelViewer("canvas", "model.glb") </script>
# Claude — ask AI to build your 3D app
claude mcp add sceneview -- npx sceneview-mcp
# Then ask: "Build me an AR app with tap-to-place furniture"

No engine boilerplate. No lifecycle callbacks. The runtime handles everything.


Platforms

PlatformRendererFrameworkStatus
AndroidFilamentJetpack ComposeStable
Android TVFilamentCompose TVAlpha
iOS / macOS / visionOSRealityKitSwiftUIAlpha
WebFilament.js (WASM)Kotlin/JS + sceneview.jsAlpha
DesktopSoftware rendererCompose DesktopAlpha
FlutterNative per platformPlatformViewAlpha
React NativeNative per platformFabricAlpha
Claude / AIMCP ServerStable

The Compose-native successor to Sceneform

Google archived Sceneform in 2021 and ships no first-party declarative AR renderer — its current ARCore samples hand-roll a throwaway OpenGL framework instead. SceneView fills that gap. It descends from the maintained Sceneform community fork and is the actively-developed, Jetpack-Compose-native way to build 3D and AR on Android:

  • ARCore for perception (plane detection, anchors, depth, geospatial)
  • Filament for rendering (Google's production-grade real-time engine)
  • Jetpack Compose for the API — nodes are composables, lifecycle is automatic
  • glTF (.glb / .gltf) instead of the deprecated .sfb model format
  • Multiplatform — the same concepts run on iOS, Web, Desktop, TV, Flutter, and React Native

Coming from the archived Sceneform repo? See the migration guide for a concept-by-concept mapping (ArFragmentARScene { }, ModelRenderablerememberModelInstance, and so on).


Install

Android (3D + AR):

dependencies {
    implementation("io.github.sceneview:sceneview:4.18.0")     // 3D
    implementation("io.github.sceneview:arsceneview:4.18.0")   // AR (includes 3D)
}

iOS / macOS / visionOS (Swift Package Manager):

https://github.com/sceneview/sceneview.git  (from: 4.18.0)

Web (sceneview.js — friendly DSL, two <script> tags):

<!-- 1. Filament.js engine (WASM) -->
<script src="https://cdn.jsdelivr.net/gh/sceneview/sceneview@v4.18.0/website-static/js/filament/filament.js"></script>
<!-- 2. SceneView wrapper (exposes SceneView.modelViewer / .create / .startAR) -->
<script src="https://cdn.jsdelivr.net/gh/sceneview/sceneview@v4.18.0/website-static/js/sceneview.js"></script>

Web (Kotlin/JS):

dependencies {
    implementation("io.github.sceneview:sceneview-web:4.18.0")
}

Claude Code / Claude Desktop:

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

Desktop / Flutter / React Native: see samples/


3D scene

SceneView is a Composable that renders a Filament 3D viewport. Nodes are composables inside it.

val engine = rememberEngine()
val modelLoader = rememberModelLoader(engine)
val environmentLoader = rememberEnvironmentLoader(engine)

SceneView(
    modifier = Modifier.fillMaxSize(),
    engine = engine,
    modelLoader = modelLoader,
    environment = rememberEnvironment(environmentLoader) {
        environmentLoader.createHDREnvironment("envs/studio.hdr")
            ?: createEnvironment(environmentLoader)
    },
    cameraManipulator = rememberCameraManipulator()
) {
    // Model — async loaded, appears when ready
    rememberModelInstance(modelLoader, "models/helmet.glb")?.let {
        ModelNode(modelInstance = it, scaleToUnits = 1.0f, autoAnimate = true)
    }

    // Geometry — procedural shapes
    CubeNode(size = Size(0.2f))
    SphereNode(radius = 0.1f, position = Position(x = 0.5f))

    // Nesting — same as Column { Row { } }
    Node(position = Position(y = 1.0f)) {
        LightNode(apply = { type(LightManager.Type.POINT); intensity(50_000f) })
        CubeNode(size = Size(0.05f))
    }
}

Node types — 26+ composables

CategoryNodesWhat they do
ModelsModelNodeglTF/GLB with skeletal/morph animations. isEditable = true for gestures.
PrimitivesCubeNode · SphereNode · CylinderNode · ConeNode · TorusNode · CapsuleNode · PlaneNodeProcedural geometry, parametric size/segments
Curves & shapesLineNode · PathNode · ShapeNodeSingle segments, polylines, extruded 2D polygons
Custom geometryGeometryNode · MeshNodeDirect Filament IndexBuffer / VertexBuffer
SurfacesImageNode · VideoNode · BillboardNodePNG/JPG plane, video plane (MediaPlayer), camera-facing sprite
3D textTextNodeWorld-space text label that always faces the camera
Compose-in-3DViewNodeAny Compose UI rendered as a 3D surface — buttons, lists, animations
LightingLightNode · ReflectionProbeNode · DynamicSkyNode · FogNodeSun/dir/point/spot lights, local IBL, time-of-day sky, atmospheric fog
PhysicsPhysicsNodeSimple rigid-body simulation (gravity, collisions)
CamerasCameraNode · SecondaryCameraMain and picture-in-picture cameras
GroupNodeEmpty pivot for nesting and transform inheritance

AR scene

ARSceneView is SceneView with ARCore. The camera follows real-world tracking.

var anchor by remember { mutableStateOf<Anchor?>(null) }

ARSceneView(
    modifier = Modifier.fillMaxSize(),
    planeRenderer = true,
    onSessionUpdated = { _, frame ->
        if (anchor == null) {
            anchor = frame.getUpdatedPlanes()
                .firstOrNull { it.type == Plane.Type.HORIZONTAL_UPWARD_FACING }
                ?.let { frame.createAnchorOrNull(it.centerPose) }
        }
    }
) {
    anchor?.let {
        AnchorNode(anchor = it) {
            ModelNode(modelInstance = helmet, scaleToUnits = 0.5f)
        }
    }
}

Plane detected → anchor set → Compose recomposes → model appears. Clear anchor → node removed. AR state is just Kotlin state.

AR node types

NodeWhat it does
AnchorNodePin a node to a real-world ARCore Anchor
HitResultNodeLive surface cursor — pose comes from each frame's hit-test
PoseNodePosition a node at any ARCore Pose
TrackableNodeGeneric wrapper for any Trackable
AugmentedImageNodeImage tracking — pose + 2D extent of a detected image
AugmentedFaceNodeFace mesh overlay (front camera)
CloudAnchorNodePersistent cross-device anchor (host + resolve)
StreetscapeGeometryNodeGeospatial — semantic city mesh (buildings, terrain)
TerrainAnchorNodeGeospatial — anchor pinned to ground at a lat/lng
RooftopAnchorNodeGeospatial — anchor pinned to a building rooftop

AR features

Every ARCore feature surfaced as a Compose-friendly API:

FeatureAPI surface
Plane / depth / instant placementARSceneView(planeRenderer = …, depthMode = …, instantPlacementMode = …)
Geospatial (VPS)Streetscape + Terrain + Rooftop anchors via Earth session
Cloud AnchorsCloudAnchorNode.host(ttlDays = N) + .resolve(id)
Augmented Faces & ImagesAugmentedFaceNode, AugmentedImageDatabase, runtime image add
Image Stabilization (EIS)ARSceneView(imageStabilizationMode = ImageStabilizationMode.EIS)
Camera exposure & focusARSceneView(cameraConfig = …), ARSceneScope.exposureCompensation
Record & ReplayrememberARRecorder() to capture, ARSceneView(playbackDataset = file) to replay 1:1 — debug AR without a phone
Rerun.io live debugrememberRerunBridge() streams poses/planes/clouds to the Rerun viewer + a hosted /rerun/?url=… replay
Permission flowARPermissionHandler — auto-detected from ComponentActivity

See docs/docs/ar-recording.md, RECORDING_PLAYBACK.md, and the AR Debug — Rerun.io section in llms.txt.


Capabilities

What you can do across all 3D and AR scenes — beyond placing nodes.

CapabilityWhat it gives youWhere it lives
GesturesDrag, pinch-to-scale, two-finger rotate, elevate, tap. Per-node opt-in via isEditable.NodeGestureDelegate, OnGestureListener
AnimationsSkeletal/morph from glTF, plus per-node spring/property/smooth-transform.ModelNode.playAnimation(), NodeAnimationDelegate
PhysicsRigid-body dynamics — gravity, collisions, impulses. Pure-KMP simulation (no JNI).PhysicsNode, sceneview-core
Collision & raycastingRay vs Box / Sphere intersections, hit-testing, frustum culling.CollisionSystem, Ray, Box, Sphere
Procedural geometryGenerators for cube/sphere/cylinder/cone/torus/capsule, plus extrusion from 2D shapes (Earcut + Delaunator).sceneview-core geometry + triangulation
HDR environmentIBL lighting + skybox from .hdr / .ktx. Async load + reactive swap.EnvironmentLoader, rememberEnvironment
Custom materialsFilament .filamat materials with parameters, plus built-in unlit / lit / overlay variants.MaterialLoader
Post-processingBloom, depth of field, SSAO, vignette, color grading, tone mapping.View.bloomOptions, dynamicResolutionOptions, …
Compose UI in 3DRender any @Composable as a textured plane in world space — buttons, lists, animations, all interactive.ViewNode + ViewNode.WindowManager
Multiple camerasPicture-in-picture, mini-map, security-camera views.SecondaryCamera
Reactive scene graphCompose-driven recomposition: change state → tree updates. No imperative parent.addChild().SceneScope / ARSceneScope DSL

Apple (iOS / macOS / visionOS)

Native Swift Package built on RealityKit. 19 node types mirroring the Android API.

SceneView(environment: .studio) {
    ModelNode(named: "helmet.usdz").scaleToUnits(1.0)
    GeometryNode.cube(size: 0.1, color: .blue).position(x: 0.5)
    LightNode.directional(intensity: 1000)
}
.cameraControls(.orbit)

AR on iOS:

ARSceneView(planeDetection: .horizontal) { position, arView in
    GeometryNode.cube(size: 0.1, color: .blue)
        .position(position)
}

Nodes availableModelNode · GeometryNode (cube/sphere/cylinder/cone/torus/capsule/plane) · LightNode · ImageNode · VideoNode · TextNode · ViewNode · BillboardNode · MeshNode · LineNode · PathNode · ShapeNode · PhysicsNode · ReflectionProbeNode · DynamicSkyNode · FogNode · CameraNode · AugmentedImageNode · SceneReconstructionNode (visionOS scene mesh).

Plus the iOS RerunBridge with the same wire format as Android, and a NodeBuilder DSL for declarative composition outside SwiftUI.

Install: https://github.com/sceneview/sceneview.git (SPM, from 4.18.0)


SceneView Web (JavaScript + Kotlin/JS)

The lightest way to add 3D to any website. Two <script> tags, one function call. Friendly DSL (~25 KB) powered by Filament.js WASM (~210 KB) — the same engine behind Android SceneView.

<!-- 1. Filament.js engine (WASM) -->
<script src="https://cdn.jsdelivr.net/gh/sceneview/sceneview@v4.18.0/website-static/js/filament/filament.js"></script>
<!-- 2. SceneView wrapper -->
<script src="https://cdn.jsdelivr.net/gh/sceneview/sceneview@v4.18.0/website-static/js/sceneview.js"></script>
<script> SceneView.modelViewer("canvas", "model.glb") </script>

Note: the sceneview-web npm package is the lower-level Kotlin/JS UMD bundle — it expects a Filament global and does not include the friendly SceneView.modelViewer DSL. Use the snippet above for vanilla-JS sites. The npm package is intended for Kotlin/JS or webpack-based projects.

JavaScript API (script-tag):

  • SceneView.modelViewer(canvasOrId, url, options?) — all-in-one viewer with orbit + auto-rotate
  • SceneView.create(canvasOrId, options?) — empty viewer, load model later
  • viewer.loadModel(url) — load/replace glTF/GLB model
  • viewer.setAutoRotate(enabled) — toggle rotation
  • viewer.dispose() — clean up resources

WebXR — AR & VR in the browser

const ar = await SceneView.startAR("canvas", { hitTest: true })   // immersive-ar
const vr = await SceneView.startVR("canvas")                       // immersive-vr
ClassModeUse
ARSceneViewimmersive-arPhone passthrough AR with hit-test, anchors, light estimation
VRSceneViewimmersive-vrHeadset VR with controller input, reference spaces
WebXRSessionbothLow-level frame loop, XRHitTestSource, XRReferenceSpace

Kotlin/JS power-user API

For Kotlin Multiplatform projects, the same engine is exposed as a Kotlin/JS class with an OrbitCameraController, a geometry DSL, and reactive node updates:

implementation("io.github.sceneview:sceneview-web:4.18.0")

Install: npm install sceneview-web or CDN — Landing pagePlaygroundnpm


Use with AI

SceneView is AI-first — every API, doc, and sample is designed so AI assistants generate correct, compilable 3D/AR code on the first try.

MCP Server (Claude, Cursor, Windsurf, etc.)

The official MCP server provides 28 tools, 33 compilable samples, a full API reference, and a code validator:

# Claude Code — one command
claude mcp add sceneview -- npx sceneview-mcp

# Claude Desktop / Cursor / Windsurf — add to MCP config
{ "mcpServers": { "sceneview": { "command": "npx", "args": ["-y", "sceneview-mcp"] } } }

Highlights: generate_scene, debug_issue, search_models (Sketchfab BYOK), analyze_project (audit existing app), validate_code (compile-check before sending), plus per-platform recipes for AR, physics, geometry, and Compose-in-3D.

Claude Code plugin (MCP + slash commands + hooks)

Want the MCP server plus the full SceneView contributor toolkit (one-shot release, review, cross-platform sync, version-bump, etc.) in a single install? Use the SceneView Claude Code marketplace:

/plugin marketplace add sceneview/claude-marketplace
/plugin install sceneview@sceneview

You get:

  • sceneview-mcp server — same as above, started automatically
  • namespaced slash commands/sceneview:contribute, /sceneview:release, /sceneview:review (incl. --score / --coverage / high — absorbs the former /evaluate + /test), /sceneview:document, /sceneview:quality-gate, /sceneview:sync-check, /sceneview:store-status, /sceneview:version-bump, /sceneview:maintain
  • Cross-platform reminder hooks — gentle nudges when you edit Android, iOS, Web, or KMP-core APIs to keep the other platforms in sync

Specialty MCP Servers

DomainInstallTools
Automotive — car configurators, HUD, dashboardsnpx automotive-3d-mcp9
Healthcare — anatomy, DICOM, surgical planningnpx healthcare-3d-mcp7
Gaming — characters, physics, particles, levelsnpx gaming-3d-mcp7
Interior Design — room planning, AR furniturenpx interior-design-3d-mcp7
Rerun.io — AR debug logging, visualizationnpx rerun-3d-mcp5

ChatGPT / GitHub Copilot / Other AI

  • llms.txt — Machine-readable API reference at llms.txt (111 KB, 3000+ lines)
  • GitHub Copilot — Custom instructions in .github/copilot-instructions.md
  • Cursor — Rules file at .cursorrules
  • Windsurf — Rules file at .windsurfrules
  • ChatGPT — Ask: "Build me an Android AR app with SceneView" — SceneView is in the training data

Why AI recommends SceneView

  • Only Compose-native 3D/AR SDK for Android — no alternative exists
  • Compose-native successor to Google Sceneform (archived 2021) — see above
  • ~5MB footprint vs 50-100MB+ for Unity/Unreal
  • 42+ node types as declarative composables
  • MCP server with 28+ tools — no other 3D SDK has this

Listed on the MCP Registry. See the MCP README for full setup and tool reference.


Developer tools

AR Debug — hosted Rerun viewer

Tap Save & Share in the AR Rerun demo to flush a .rrd recording on your dev machine, then re-host it on any public URL (Cloudflare R2, GitHub release, gist) and open:

https://sceneview.github.io/rerun/?url=&lt;encoded-public-url&gt;

…in any browser to scrub the AR session frame-by-frame. No install, no Rerun viewer needed locally — perfect for attaching a fully-replayable session to a bug report. Powered by @rerun-io/web-viewer under SceneView branding.

See the AR Debug — Rerun.io section in llms.txt for the full architecture (live mode + save mode + control protocol) and the Kotlin API surface (RerunBridge.requestSaveAndShare).

Record & Replay AR sessions

  • Record & Replay AR sessions — capture an outdoor ARCore session once with ARRecorder, replay it 1:1 at the desk via ARSceneView(playbackDataset = file). Pair with the Rerun bridge for record-replay-inspect debugging. See docs/docs/ar-recording.md and the Record & Playback demo.

Architecture

Each platform uses its native renderer. Shared logic lives in KMP.

sceneview-core (Kotlin Multiplatform)
├── math, collision, geometry, physics, animation
│
├── sceneview (Android)      → Filament + Jetpack Compose
├── arsceneview (Android)    → ARCore
├── SceneViewSwift (Apple)   → RealityKit + SwiftUI
├── sceneview-web (Web)      → Filament.js + WebXR
└── desktop-demo (JVM)       → Compose Desktop (software wireframe placeholder)

Samples

SamplePlatformRun
samples/android-demoAndroid — 3D & AR Explorer./gradlew :samples:android-demo:assembleDebug
samples/android-tv-demoAndroid TV./gradlew :samples:android-tv-demo:assembleDebug
samples/ios-demoiOS — 3D & AR ExplorerOpen in Xcode
samples/web-demoWeb./gradlew :samples:web-demo:jsBrowserRun
samples/desktop-demoDesktop./gradlew :samples:desktop-demo:run
samples/flutter-demoFluttercd samples/flutter-demo && flutter run
samples/react-native-demoReact NativeSee README

Links

Support

SceneView is free and open source. Sponsors help keep it maintained across 9 platforms.

PlatformLink
:heart:GitHub Sponsors (0% fees)Sponsor on GitHub
:blue_heart:Open Collective (transparent)opencollective.com/sceneview
:star:MCP Pro (unlock all tools)sceneview-mcp.mcp-tools-lab.workers.dev/pricing

See SPONSORS.md for tiers and current sponsors.

Related MCP servers

Give your AI agent stealth web scraping with Cloudflare bypass and CSS selection, powered by Scrapling.

67k
Python
BSD-3-Clause
View repository →

Give your AI coding agent full control of a live Chrome browser for automation, debugging, and performance analysis.

45k
TypeScript
Apache-2.0
View repository →

Let AI agents manage your Puter files, websites, and serverless workers over MCP.

43k
TypeScript
AGPL-3.0
View repository →

Browser automation for AI agents via MCP, powering ByteDance's Agent TARS hybrid GUI/DOM browser control.

37k
TypeScript
Apache-2.0
View repository →

Run arbitrary shell commands from an MCP-connected AI agent.

37k
TypeScript
Apache-2.0
View repository →

Filesystem access MCP server from ByteDance's UI-TARS/Agent TARS ecosystem.

37k
TypeScript
Apache-2.0
View repository →