npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

meshy-mcp

v1.0.0

Published

MCP server for Meshy AI auto-rigging and animation API

Readme

Meshy MCP Server

MCP (Model Context Protocol) server that exposes Meshy AI's auto-rigging and animation API as tools for Claude and other MCP clients.

Features

  • Auto-rigging: Convert static GLB/FBX humanoid models into rigged characters with skeletons
  • Animation: Apply animations from Meshy's library to rigged characters
  • Async polling: Built-in polling with exponential backoff for long-running tasks
  • Balance checking: Monitor API credit balance

Installation

npm install meshy-mcp

Or run directly with npx:

npx meshy-mcp

Configuration

Set the MESHY_API_KEY environment variable:

export MESHY_API_KEY=msy_your_api_key_here

Get your API key from Meshy API Settings.

Available Tools

| Tool | Description | |------|-------------| | meshy_create_rigging_task | Start auto-rigging job for a 3D humanoid model | | meshy_get_rigging_task | Get rigging task status and results | | meshy_poll_rigging_task | Poll rigging task until completion (with timeout) | | meshy_delete_rigging_task | Cancel/delete a rigging task | | meshy_create_animation_task | Apply animation to rigged character | | meshy_get_animation_task | Get animation task status | | meshy_get_balance | Check API credit balance |

Usage with Claude Code

Add to your .mcp.json or MCP proxy configuration:

{
  "mcpServers": {
    "meshy": {
      "command": "npx",
      "args": ["-y", "meshy-mcp"],
      "env": {
        "MESHY_API_KEY": "${MESHY_API_KEY}"
      }
    }
  }
}

Example Workflow

1. Check balance first

meshy_get_balance()

2. Create a rigging task

meshy_create_rigging_task(
  model_url="https://example.com/character.glb",
  height_meters=1.8
)

Returns: { "task_id": "task-uuid-here" }

3. Poll for completion

meshy_poll_rigging_task(
  task_id="task-uuid-here",
  timeout_ms=300000
)

Returns task with output URLs when complete:

{
  "success": true,
  "task": {
    "id": "task-uuid-here",
    "status": "SUCCEEDED",
    "progress": 100,
    "result": {
      "rigged_character_glb_url": "https://assets.meshy.ai/...",
      "rigged_character_fbx_url": "https://assets.meshy.ai/...",
      "basic_animations": {
        "walking_glb_url": "https://...",
        "running_glb_url": "https://..."
      }
    }
  }
}

4. Apply additional animation

meshy_create_animation_task(
  rig_task_id="task-uuid-here",
  action_id=1,
  fps=30
)

Tool Parameters

meshy_create_rigging_task

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | model_url | string | * | Publicly accessible GLB file URL | | input_task_id | string | * | Completed Meshy task ID (alternative to model_url) | | height_meters | number | No | Character height in meters (0.1-10, default: 1.7) |

* Either model_url or input_task_id is required

meshy_poll_rigging_task

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | task_id | string | Yes | The rigging task ID to poll | | timeout_ms | number | No | Maximum wait time (10000-600000, default: 300000) |

meshy_create_animation_task

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | rig_task_id | string | Yes | Completed rigging task ID | | action_id | number | Yes | Animation action ID from Meshy library | | fps | number | No | Target frame rate (24, 25, 30, or 60) |

Supported Models

Auto-rigging works best with:

  • Textured humanoid (bipedal) models
  • GLB or FBX format
  • Clear limb and body structure
  • Standard proportions

Not recommended for:

  • Untextured meshes
  • Non-humanoid assets (animals, objects, vehicles)
  • Characters with unclear body structure
  • Very stylized proportions

Error Handling

All tools return structured error responses:

{
  "success": false,
  "error": "Meshy API Error (401): Invalid API key"
}

Common error codes:

  • 401: Invalid or missing API key
  • 404: Task not found
  • 408: Polling timeout (task still processing)
  • 429: Rate limit exceeded
  • 500: Server error or task failed

Development

# Install dependencies
npm install

# Build
npm run build

# Run tests
npm test

# Watch mode
npm run build:watch

License

MIT