jasonjgardner/blockbench-mcp-plugin

开发工具

本页由 AI 翻译，技术细节请以原文为准。查看原文

593 stars 62 forks 质量 88 趋势 46GPL-3.0

Repository Install

jasonjgardner/blockbench-mcp-plugin 是从 https://github.com/jasonjgardner/blockbench-mcp-plugin. 导入的 MCP 服务器候选。

概览

jasonjgardner/blockbench-mcp-plugin 是从 https://github.com/jasonjgardner/blockbench-mcp-plugin. 导入的 MCP 服务器候选。

概述（AI 翻译）

演示卷轴

https://github.com/user-attachments/assets/c67d0dd8-ee50-40ba-b308-a84a21772901

所有通过Blockbench MCP插件使用代理技能创建的场景、模型和纹理。（在Blender中渲染）

插件安装

打开桌面版 Blockbench，进入插件>文件，点击“从 URL 加载插件”，然后粘贴这个 URL：

https://jasonjgardner.github.io/blockbench-mcp-plugin/mcp.js

模型上下文协议服务器

该仓库包含两种MCP服务器选项。

无头 `.bbmodel` （标准）

一个独立的stdio MCP服务器负责直接编辑、验证、转换和渲染.bbmodel文件，无需运行Blockbench。每个代理可以启动自己的进程，因此多个代理可以并行工作，同时你继续使用编辑器。直接从GitHub运行：

请参阅 headless/README.md 以了解客户端配置、工具列表和限制。

Blockbench 桌面插件（HTTP）

在Blockbench设置下配置MCP服务器：设置>通用>MCP服务器端口和MCP服务器端点。

以下安装设置示例使用默认值 :3000/bb-mcp

安装

本页由 AI 翻译，技术细节请以原文为准。

README

以下为原文 README 节选，完整内容请查看原文。

Blockbench MCP

Plugin Installation

Open the desktop version of Blockbench, go to File > Plugins and click the “Load Plugin from URL” and paste in this URL:

https://jasonjgardner.github.io/blockbench-mcp-plugin/mcp.js

Model Context Protocol Servers

This repository contains two MCP server options.

Headless `.bbmodel` (stdio)

A separate stdio MCP server edits, validates, converts and renders .bbmodel files directly, without Blockbench running. Each agent can start its own process, so several can work in parallel while you keep using the editor. Run it straight from GitHub:

npx -y github:jasonjgardner/blockbench-mcp-plugin --root ./models

See headless/README.md for client configuration, the tool list and limits.

Blockbench Desktop Plugin (HTTP)

Configure the MCP server under Blockbench settings: Settings > General > MCP Server Port and MCP Server Endpoint.

The following installation settings examples use the default values of :3000/bb-mcp

Installation

The examples below configure the desktop plugin over HTTP and the headless server over stdio. You can use either server or both. HTTP requires Blockbench running with the plugin installed; stdio requires Node.js with npm and starts its own server process.

For headless examples, replace /path/to/models with an absolute path to your model directory (for example, C:/Users/you/models on Windows). --root is required and limits file access to that directory.

On Windows, clients that cannot launch npx directly should use "command": "cmd" and prepend "/c", "npx" to args, as shown for Claude Desktop.

.vscode/mcp.json

{
  "servers": {
    "blockbench": {
      "url": "http://localhost:3000/bb-mcp",
      "type": "http"
    },
    "bbmodel": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "github:jasonjgardner/blockbench-mcp-plugin",

在 GitHub 查看完整 README

安装

npx -y github:jasonjgardner/blockbench-mcp-plugin --root ${input:rootDir}

新手？先看 mcpskill.org 教程 →

配置

{
  "mcpServers": {
    "blockbench": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "http://localhost:3000/bb-mcp"]
    },
    "bbmodel": {
      "command": "npx",
      "args": ["-y", "github:jasonjgardner/blockbench-mcp-plugin", "--root", "/path/to/models"]
    }
  }
}