meshy-ai
This is a Model Context Protocol (MCP) server for interacting with the Meshy AI API. It provides tools for generating 3D models from text and images, applying textures, and remeshing models.
claude mcp add --transport stdio pasie15-meshy-ai-mcp-server npx -y meshy-ai-mcp-server \ --env MESHY_API_KEY="your_meshy_api_key_here"
How to use
Meshy AI MCP Server exposes a suite of tools that bridge MCP clients with Meshy AI's generative 3D capabilities. It supports text-to-3D generation, image-to-3D conversion, texturing, remeshing, rigging, and animation, with streaming for real-time task updates. Clients such as Claude Desktop, Cursor, or VS Code integrations can issue tasks like create_text_to_3d_task, create_image_to_3d_task, or create_remesh_task and then poll or stream results as they become available. The server handles authentication via a Meshy API key, and you can tailor request behavior through optional environment variables for API base endpoints and streaming timeouts.
How to install
Prerequisites:
- Node.js and npm installed on your system
- Access to a Meshy AI API key
Option 1 — Run directly with npx (Recommended):
# Run the MCP server directly without local installation
Configure and run via the MCP config (example):
{
"mcpServers": {
"meshy-ai": {
"command": "npx",
"args": [
"-y",
"meshy-ai-mcp-server"
],
"env": {
"MESHY_API_KEY": "your_meshy_api_key_here"
}
}
}
}
Option 2 — Clone and Build Locally:
# 1) Clone the repository
git clone <repository-url>
cd meshy-ai-mcp-server
# 2) Install dependencies
npm install
# 3) Build the project (if applicable)
npm run build
Configure your MCP client to point at the local server path (example):
{
"mcpServers": {
"meshy-ai": {
"command": "node",
"args": [
"/absolute/path/to/meshy-ai-mcp-server/dist/index.js"
],
"env": {
"MESHY_API_KEY": "your_meshy_api_key_here"
}
}
}
}
Additional notes
Environment variables:
- MESHY_API_KEY: Required. Your Meshy API key.
- MESHY_API_BASE: Optional. Override the API base URL (default: https://api.meshy.ai/openapi).
- MESHY_STREAM_TIMEOUT_MS: Optional. Streaming timeout in milliseconds (default: 300000). Common issues:
- Ensure your API key has the proper permissions on Meshy.
- If using npx, network access is required to fetch the package from npm.
- When configuring clients, provide the absolute path to the built server file if using a local install.
- For long-running tasks, verify your streaming timeout to prevent premature disconnects.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.