MCP.so
ログイン

Tripo MCP Server

@VAST-AI-Research

Tripo MCP Server について

Official MCP server for Tripo

基本情報

カテゴリ

その他

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

VAST-AI-Research

投稿者

Yanpei Cao

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "tripo-mcp": {
      "command": "uvx",
      "args": [
        "tripo-mcp"
      ]
    }
  }
}

ツール

15

Get detailed information about the current Blender scene

Get detailed information about a specific object in the Blender scene. Parameters: - object_name: The name of the object to get information about

Create a new object in the Blender scene. Parameters: - type: Object type (CUBE, SPHERE, CYLINDER, PLANE, CONE, TORUS, EMPTY, CAMERA, LIGHT) - name: Optional name for the object - location: Optional [x, y, z] location coordinates - rotation: Optional [x, y, z] rotation in radians - scale: Optional [x, y, z] scale factors

Modify an existing object in the Blender scene. Parameters: - name: Name of the object to modify - location: Optional [x, y, z] location coordinates - rotation: Optional [x, y, z] rotation in radians - scale: Optional [x, y, z] scale factors - visible: Optional boolean to set visibility

Delete an object from the Blender scene. Parameters: - name: Name of the object to delete

Set or create a material for an object. Parameters: - object_name: Name of the object to apply the material to - material_name: Optional name of the material to use or create - color: Optional [R, G, B] color values (0.0-1.0)

Execute arbitrary Python code in Blender. Parameters: - code: The Python code to execute

Get a list of categories for a specific asset type on Polyhaven. Parameters: - asset_type: The type of asset to get categories for (hdris, textures, models, all)

Search for assets on Polyhaven with optional filtering. Parameters: - asset_type: Type of assets to search for (hdris, textures, models, all) - categories: Optional comma-separated list of categories to filter by Returns a list of matching assets with basic information.

Download and import a Polyhaven asset into Blender. Parameters: - asset_id: The ID of the asset to download - asset_type: The type of asset (hdris, textures, models) - resolution: The resolution to download (e.g., 1k, 2k, 4k) - file_format: Optional file format (e.g., hdr, exr for HDRIs; jpg, png for textures; gltf, fbx for models) Returns a message indicating success or failure.

Apply a previously downloaded Polyhaven texture to an object. Parameters: - object_name: Name of the object to apply the texture to - texture_id: ID of the Polyhaven texture to apply (must be downloaded first) Returns a message indicating success or failure.

Check if PolyHaven integration is enabled in Blender. Returns a message indicating whether PolyHaven features are available.

Create a 3D model from a text description using the Tripo API. IMPORTANT: This tool initiates a 3D model generation task but does NOT wait for completion. After calling this tool, you MUST repeatedly call the get_task_status tool with the returned task_id until the task status is SUCCESS or a terminal error state. Typical workflow: 1. Call create_3d_model_from_text to start the task 2. Get the task_id from the response 3. Call get_task_status with the task_id 4. If status is not SUCCESS, wait a moment and call get_task_status again 5. Repeat until status is SUCCESS or a terminal error state 6. When status is SUCCESS, use the pbr_model_url from the response Args: describe_the_look_of_object: A detailed description of the object to generate. face_limit: The maximum number of faces in the model. auto_size: Whether to automatically size the model. Returns: A dictionary containing the task ID and instructions for checking the status.

Import a GLB model from URL into Blender scene Parameters: - glb_url: Download URL of the GLB model file Returns: Result message of the import operation

Get the status of a 3D model generation task. IMPORTANT: This tool checks the status of a task started by create_3d_model_from_text. You may need to call this tool MULTIPLE TIMES until the task completes. Typical workflow: 1. Call this tool with the task_id from create_3d_model_from_text 2. Check the status in the response: - If status is SUCCESS, the task is complete and you can use the pbr_model_url - If status is FAILED, CANCELLED, BANNED, or EXPIRED, the task failed - If status is anything else, the task is still in progress 3. If the task is still in progress, wait a moment and call this tool again Args: task_id: The ID of the task to check (obtained from create_3d_model_from_text). Returns: A dictionary containing the task status and other information.

概要

What is Tripo MCP Server?

Tripo MCP provides an interface between AI assistants and Tripo AI via the Model Context Protocol (MCP). It enables 3D asset generation from natural language and imports models into Blender through the Tripo AI Blender Addon. The project is in alpha and currently supports only Blender integration.

How to use Tripo MCP Server?

Install Python 3.10+, Blender, the Tripo AI Blender Addon, and an MCP-enabled AI assistant (Claude Desktop or Cursor IDE). Configure the MCP server by running pip install uv and adding the JSON configuration to Cursor or Claude. After enabling the addon and starting the Blender MCP server, chat with the assistant (e.g., “Generate a 3D model of a futuristic chair”) to create 3D assets.

Key features of Tripo MCP Server

  • Generate 3D assets from natural language using Tripo’s API
  • Import generated models directly into Blender
  • Compatible with Claude and other MCP-enabled AI assistants
  • Integrates with the Tripo AI Blender Addon

Use cases of Tripo MCP Server

  • Quickly prototype a 3D chair model from a text description
  • Generate 3D assets for Blender scenes via conversational AI
  • Automate 3D modeling tasks within a Blender workflow

FAQ from Tripo MCP Server

What dependencies are required?

You need Python 3.10+, Blender, the Tripo AI Blender Addon, and an MCP-enabled AI assistant such as Claude Desktop or Cursor IDE.

How do I configure the MCP server?

Install uv with pip, then add the JSON configuration referencing "command": "uvx" and "args": ["tripo-mcp"] to your MCP client (Cursor or Claude Desktop).

Is Tripo MCP Server production-ready?

No, the project is in alpha. It currently supports only Tripo Blender Addon integration.

What can I do after setup?

Enable the Tripo AI Blender Addon, start the Blender MCP server, and then chat with the AI assistant (e.g., “Generate a 3D model of a futuristic chair”) to create 3D assets and import them into Blender.

Does it support AI assistants other than Claude?

The README mentions Claude and other MCP-enabled assistants, and specifically lists Claude for Desktop and Cursor IDE as compatible options.

コメント

「その他」の他のコンテンツ