3Dawn MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@3Dawn MCP ServerGenerate a low-poly fox 3D model"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
What is this?
The 3Dawn MCP Server exposes the full 3Dawn platform to any AI assistant via the Model Context Protocol (MCP).
Connect it to Claude, ChatGPT, Cursor, or any MCP client and ask your AI to:
"Generate a cartoon robot 3D model and mint it as an NFT" "List all assets in my wallet and put the best one on the marketplace for 0.1 ETH" "What drops are active right now? How much have I earned from embeds?"
Transport: Streamable HTTP โ works with remote Claude.ai integrations and local clients.
Related MCP server: Meshy MCP Server
๐ ๏ธ Available Tools
๐จ Generation
Tool | Description |
| Start a text โ 3D job (Meshy AI backend) |
| Poll a job until |
| Apply a refinement pass to an existing model |
๐ฆ Assets
Tool | Description |
| All 3D assets owned by a wallet |
| Full details for a specific asset |
| Trending / featured assets on the platform |
| Get iframe embed code (earns $0.02/view) |
| View count + earnings analytics for an asset |
๐ Marketplace
Tool | Description |
| Browse listings โ filter by ETH or stock payment |
| Full details for a specific listing |
๐ฐ Drops
Tool | Description |
| Browse drops by status (active / sold_out / ended) |
| Bonding curve, slots, countdown for a specific drop |
๐ค User & Earnings
Tool | Description |
| Creator stats: assets, mints, listings, drops |
| Detailed earnings: embed yield, sales, drops |
๐ Platform
Tool | Description |
| Live platform-wide statistics |
| Latest mints, sales, drops across the platform |
| All tokenized stocks with live prices |
๐ Quick Start
Prerequisites
Python 3.11+
pip
Install
git clone https://github.com/3DawnRH/3dawn-mcp.git
cd 3dawn-mcp
pip install -r requirements.txtConfigure
cp .env.example .envEdit .env:
# Required โ point at the live platform or your self-hosted instance
3DAWN_API_URL=https://3dawn.xyz
# Optional โ override the default port (8000)
# PORT=8000โ No API keys needed to run the MCP server itself. The server talks to the public 3Dawn REST API.
Run
python server.pyThe server listens on http://0.0.0.0:8000/mcp (Streamable HTTP transport).
๐ Connect to Claude.ai
Go to Claude.ai โ Settings โ Integrations โ Add MCP Server
Enter your server URL:
https://your-host:8000/mcpClick Connect
For local testing, use a tunnel:
# Using ngrok
ngrok http 8000
# Then add the ngrok URL to Claude๐ Connect to Cursor / Local Clients
Add to your ~/.cursor/mcp.json (or equivalent):
{
"mcpServers": {
"3dawn": {
"url": "http://localhost:8000/mcp"
}
}
}๐ก Example Prompts
Once connected to Claude or another AI:
Generate a sci-fi spaceship 3D model in realistic style for my wallet 0x1234โฆBrowse the 3Dawn marketplace and find the cheapest ETH listing. Show me its 3D model.How many total assets have been created on 3Dawn? What are the top creators earning?List all my assets at wallet 0xABCDโฆ and tell me which ones are listed for sale.Check the embed analytics for asset ID 42 โ how much has it earned so far?๐๏ธ Architecture
3dawn-mcp/
โโโ server.py # FastMCP server โ all 18 tools defined here
โโโ client.py # Async HTTP client wrapping the 3Dawn REST API
โโโ requirements.txt
โโโ .env.exampleDependencies:
Package | Purpose |
| Model Context Protocol SDK |
| Async HTTP for API calls |
|
|
๐งช Testing Tools Manually
# Install MCP inspector
npx @modelcontextprotocol/inspector http://localhost:8000/mcpOr use curl:
# List all tools
curl http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'๐ง Self-Hosting 3Dawn
To point the MCP server at your own 3Dawn instance:
3DAWN_API_URL=https://your-3dawn-instance.comSee 3dawn-app for self-hosting instructions.
๐ค Contributing
See CONTRIBUTING.md. PRs welcome โ especially new tools!
๐ Security
See SECURITY.md for vulnerability reporting.
๐ License
MIT โ see LICENSE
This server cannot be deployed
Maintenance
Related MCP Connectors
Generate and edit images, video, voice, lip-sync and 3D models from your AI agent.
- SkilderOAuthai.skilder
One place to build, share, and govern the skills and tools your AI agents use at work.
3D avatars, embeds, glTF tools, agent memory, and on-chain agent identity from three.ws.
- OwlCADOAuthcom.owlcad
Parametric 3D CAD for AI agents: build print-ready parts, check them, export STL, 3MF or STEP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with the Tripo3D AI API to generate 3D models from text, images, or multiview inputs. It supports advanced features like model animation, stylization, and real-time task status tracking.81 npm5ISC

Meshy MCP Serverofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to create, manage, and download 3D models, textures, images, rigged characters, and animations through natural conversation.1,637 npm46MIT- AlicenseAqualityDmaintenanceEnables AI assistants to generate 3D models, textures, and images via the Meshy API using natural language, supporting text-to-3D, image-to-3D, remeshing, retexturing, rigging, and animation workflows.3628 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to control CLO3D for pattern creation, fabric swapping, simulation, and model export via natural language commands.26MIT