jasonjgardner/blockbench-mcp-plugin

Adds MCP server to Blockbench

What it solves

This project enables AI agents to interact with Blockbench, a popular 3D modeling software. It bridges the gap between AI assistants and creative design tools, allowing agents to programmatically create, edit, and manage 3D models.

How it works

It implements the Model Context Protocol (MCP) to expose Blockbench functions as tools that an AI agent can call. It provides two modes: a desktop plugin that communicates over HTTP while the Blockbench application is running, and a headless server that can manipulate .bbmodel files directly via the command line without needing the full GUI.

Who it’s for

This is for developers and creators who want to automate 3D asset generation or integrate AI agents into their 3D modeling workflow using tools like Claude Desktop, Cline, or VS Code.

Highlights

  • Supports both interactive desktop automation and headless file manipulation.
  • Compatible with various MCP-enabled AI clients including Claude, Cline, and Ollama.
  • Allows other Blockbench plugins to register custom tools via a global queue.
  • Includes security features like loopback-only networking and optional disabling of arbitrary code execution (risky_eval).

Related

  • Project
    neka-nat/freecad-mcp

    A Model Context Protocol (MCP) server that enables AI assistants to control FreeCAD for 3D modeling, script execution, and FEM analysis.

  • Project
    matlab/matlab-mcp-server

    MATLAB MCP Server is a Go‑based bridge that lets AI assistants (Claude, Copilot, Codex, etc.) start MATLAB, run scripts, perform static analysis, and run unit tests via the Model Context Protocol. It supports configurable launch options, custom tool extensions, and provides coding‑guideline resources. Install MATLAB R2021a+, download the binary, and integrate it with your AI tool using the provided CLI snippets.

  • Project
    AnkleBreaker-Studio/unity-mcp-server

    AnkleBreaker Unity MCP is a Model Context Protocol server that lets AI assistants control multiple Unity editors simultaneously — building scenes, running tests, managing multiplayer Play Mode, and inspecting performance — with per-editor queues, action history, and undo support. It's built for teams coordinating several agents across projects and demanding Unity workflows.

  • Project
    hkr04/cpp-mcp

    A C++ implementation of the Model Context Protocol (MCP) that allows AI models and agents to interact with tools, resources, and services through a standardized interface.

  • Project
    mixelpixx/KiCAD-MCP-Server

    A Model Context Protocol (MCP) server that enables AI assistants to automate PCB design in KiCAD using natural language commands.