Blender Ai Mcp

Created By
PatrykIti6 months ago
Modular MCP Server + Blender Addon for AI-Driven 3D Modeling. Enable LLMs (Claude, ChatGPT) to control Blender reliably. Built with Clean Architecture for stability and scalability.
Overview

What is Blender Ai Mcp?

Blender Ai Mcp is a modular server and Blender addon designed to enable AI-driven 3D modeling by allowing large language models (LLMs) like Claude and ChatGPT to control Blender reliably. It is built with a clean architecture for stability and scalability.

How to use Blender Ai Mcp?

To use Blender Ai Mcp, run the provided Docker command to set up the server, and then interact with Blender through the AI to create and manipulate 3D models.

Key features of Blender Ai Mcp?

  • Reliable control of Blender through AI without the need for raw Python scripting.
  • Error handling and feedback loop for AI-generated scripts.
  • Modular architecture for easy updates and scalability.

Use cases of Blender Ai Mcp?

  1. Automating the creation of complex 3D models such as biological structures and mechanical parts.
  2. Enhancing the workflow of 3D artists by integrating AI assistance in modeling tasks.
  3. Providing a stable environment for AI to interact with Blender's internal state.

FAQ from Blender Ai Mcp?

  • Can Blender Ai Mcp handle all Blender operations?

Yes, it is designed to manage a wide range of operations, from scene management to complex modeling tasks.

  • Is Blender Ai Mcp free to use?

The project is open-source and can be used freely under its license.

  • How does Blender Ai Mcp ensure safety?

It uses sandboxed endpoints with validated inputs to minimize risks associated with executing arbitrary Python code.

Server Config

{
  "mcpServers": {
    "blender-ai-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "BLENDER_RPC_HOST=host.docker.internal",
        "ghcr.io/patrykiti/blender-ai-mcp:latest"
      ],
      "disabled": false,
      "autoApprove": [
        "scene_list_objects",
        "scene_delete_object",
        "scene_clean_scene",
        "scene_duplicate_object",
        "scene_set_active_object",
        "scene_get_viewport",
        "scene_create_light",
        "scene_create_camera",
        "scene_create_empty",
        "modeling_create_primitive",
        "modeling_transform_object",
        "modeling_add_modifier",
        "modeling_apply_modifier",
        "modeling_convert_to_mesh",
        "modeling_join_objects",
        "modeling_separate_object",
        "modeling_set_origin",
        "modeling_list_modifiers"
      ]
    }
  }
}
Project Info
Created At
6 months ago
Updated At
6 months ago
Author Name
PatrykIti
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago