@modelcontextprotocol/server-threejs
MCP ServerFreeThree.js 3D visualization MCP App Server
Capabilities8 decomposed
three.js scene graph exposure via mcp protocol
Medium confidenceExposes Three.js 3D scene objects (geometries, materials, meshes, lights, cameras) as MCP resources that LLM clients can query and manipulate. Implements a resource-based MCP server that maps Three.js scene hierarchy to a queryable interface, allowing remote clients to introspect scene state, object properties, and spatial relationships without direct WebGL access.
Bridges Three.js 3D scenes directly into MCP protocol as queryable resources, enabling LLMs to reason about 3D geometry and scene structure without WebGL rendering context — uses MCP resource handlers to map Three.js object hierarchy into a standardized interface
Unique in exposing Three.js scenes to MCP-compatible LLMs (Claude, etc.) rather than requiring custom REST APIs or WebSocket servers for 3D scene introspection
mcp tool registration for 3d object manipulation
Medium confidenceRegisters MCP tools that allow LLM clients to create, modify, and delete Three.js objects (meshes, lights, cameras) through standardized tool-calling interfaces. Implements tool handlers that translate LLM function calls into Three.js API operations, with schema validation for geometry parameters, material properties, and transform operations.
Implements MCP tool handlers that directly invoke Three.js constructors and methods, with schema validation for geometry types (BoxGeometry, SphereGeometry, etc.) and material properties — uses a registry pattern to map tool names to Three.js operations
Tighter integration with Three.js API than generic REST-based 3D APIs, reducing serialization overhead and enabling direct object references within the same Node.js process
real-time scene synchronization with mcp clients
Medium confidenceMaintains bidirectional state synchronization between the Three.js scene and connected MCP clients, pushing scene updates (object creation, deletion, property changes) to clients and receiving commands from clients to modify the scene. Uses MCP notifications or polling mechanisms to keep client representations of the scene state consistent with server-side changes.
Uses MCP notification protocol to push Three.js scene changes to clients in real-time, rather than requiring clients to poll for updates — implements event listeners on Three.js objects to detect changes and broadcast them via MCP
More efficient than REST polling for real-time 3D updates, and leverages MCP's native notification system rather than requiring WebSocket fallbacks
geometry and material parameter schema generation
Medium confidenceAutomatically generates JSON schemas for Three.js geometry constructors and material properties, enabling MCP clients to understand valid parameters for creating and modifying 3D objects. Introspects Three.js class definitions to extract parameter names, types, and constraints, then exposes these schemas as MCP resources or tool definitions.
Dynamically generates MCP-compatible schemas from Three.js class definitions, allowing LLMs to discover valid parameters without hardcoded schema files — uses reflection or static analysis to extract constructor signatures
Reduces manual schema maintenance compared to hand-written parameter definitions, and keeps schemas in sync with Three.js library versions
camera and viewport control via mcp
Medium confidenceExposes Three.js camera and viewport controls (position, rotation, field of view, aspect ratio) as MCP tools and resources, allowing LLM clients to adjust the viewing perspective of the 3D scene. Implements camera manipulation handlers that translate LLM commands into Three.js camera transformations and viewport updates.
Exposes Three.js camera as an MCP-controllable resource with tools for position, rotation, and projection adjustments — implements camera state tracking and validation to prevent invalid configurations
Enables LLM-driven camera control without requiring custom camera management code, leveraging Three.js's native camera API
scene export and serialization to standard formats
Medium confidenceExports Three.js scenes to standard 3D file formats (glTF/glB, OBJ, FBX) or JSON representations that can be persisted, shared, or imported into other 3D tools. Implements serialization handlers that traverse the scene graph, extract geometry and material data, and write to disk or return as structured data.
Integrates Three.js exporters (GLTFExporter, OBJExporter) as MCP tools, allowing LLM clients to trigger scene exports without direct file system access — handles asset path resolution and format-specific options
Provides standardized export workflows compared to manual exporter configuration, and enables LLM-driven scene persistence without custom serialization code
lighting and material property adjustment
Medium confidenceExposes Three.js lighting (ambient, directional, point, spot lights) and material properties (color, metalness, roughness, emissive, opacity) as MCP tools and resources. Implements handlers for modifying light intensity, color, position, and material parameters, with real-time updates to the scene rendering.
Exposes Three.js lighting and material systems as MCP tools with parameter validation and real-time updates — implements handlers for all standard Three.js light types and PBR material properties
Enables LLM-driven lighting and material design without requiring manual Three.js API calls, and provides a unified interface for adjusting scene appearance
scene query and spatial analysis via mcp
Medium confidenceProvides MCP tools for querying scene structure and performing spatial analysis: finding objects by name or type, calculating bounding boxes, measuring distances between objects, detecting intersections, and traversing the scene hierarchy. Implements query handlers that use Three.js raycasting and bounding box calculations to answer spatial questions.
Implements MCP tools for Three.js spatial queries using native raycasting and bounding box APIs — enables LLMs to reason about scene geometry without direct WebGL access
Provides spatial analysis capabilities that would otherwise require custom geometry libraries or external physics engines
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with @modelcontextprotocol/server-threejs, ranked by overlap. Discovered automatically through the match graph.
@modelcontextprotocol/server-shadertoy
MCP App Server example for rendering ShaderToy-compatible GLSL shaders
@mcp-monorepo/weather
Weather MCP tools (geocoding, weather-by-coords) for ModelContextProtocol.
@modelcontextprotocol/server-basic-solid
Basic MCP App Server example using Solid
@modelcontextprotocol/server-map
MCP App Server example with CesiumJS 3D globe and geocoding
ECharts
** - Generate visual charts using [ECharts](https://echarts.apache.org) with AI MCP dynamically, used for chart generation and data analysis.
Maya MCP
** - MCP server for Autodesk Maya
Best For
- ✓AI agents building or analyzing 3D scenes
- ✓LLM-powered 3D design tools
- ✓Teams integrating Three.js with Claude or other MCP-compatible LLMs
- ✓Developers building AI-powered 3D design interfaces
- ✓Teams using Claude or other MCP-compatible LLMs for 3D content creation
- ✓Prototyping LLM-driven 3D visualization tools
- ✓Collaborative 3D design tools with LLM assistance
- ✓Real-time 3D visualization dashboards
Known Limitations
- ⚠Read-only or limited write access to scene graph depending on implementation — cannot guarantee real-time bidirectional sync
- ⚠No built-in support for complex shader code introspection or custom material parameters beyond standard Three.js materials
- ⚠Latency overhead from MCP protocol serialization for large scenes with thousands of objects
- ⚠Tool schema must be predefined — cannot dynamically expose all Three.js parameters without explicit tool registration
- ⚠No built-in undo/redo system — state changes are immediate and require external transaction management
- ⚠Limited error recovery — invalid geometry parameters may fail silently or crash the scene
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
Package Details
About
Three.js 3D visualization MCP App Server
Categories
Alternatives to @modelcontextprotocol/server-threejs
Are you the builder of @modelcontextprotocol/server-threejs?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →