godot-mcp: 一款支持godot开源引擎的的mcp插件,支持常见godot引擎操作,一键配置服务

by DaxianLee · MCP Server · ★ 535

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Featured in: Blender, Unity & Godot MCP

How to install godot-mcp

git clone https://github.com/DaxianLee/godot-mcp.git
claude mcp add --scope <user|project> --transport http godot-mcp http://127.0.0.1:3000/mcp

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 64/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

Stars535
Forks66
LanguageGDScript
CategoryMCP Server
Quality Score64/100
Open Issues9
Last Updated2026-01-14
Created2026-01-01
Platformscli, mcp
Est. Tokens~15k

About godot-mcp

Godot MCP Server English | 中文 一个为 Godot 引擎设计的 Model Context Protocol (MCP) 服务器插件,让 AI 助手能够直接与 Godot 编辑器交互,实现 AI 驱动的游戏开发。 功能特性 核心功能 场景管理 - 创建、打开、保存场景,查看场景树结构 节点操作 - 添加、删除、移动节点,修改节点属性 脚本编辑 - 创建、读取、修改 GDScript 脚本 资源管理 - 加载、创建、修改游戏资源 文件系统 - 浏览项目文件,读写文件内容 编辑器控制 - 控制编辑器界面,管理选中对象、撤销重做 调试工具 - 查看日志,获取运行时信息 动画工具 - 创建和编辑动画,状态机管理 视觉效果 材质工具 - 创建和配置材质 着色器工具 - 管理着色器参数 灯光工具 - 配置场景灯光 粒子工具 - 创建粒子效果 2D 开发 瓦片地图工具 -...

Compatible Skills

These tools work well together with godot-mcp for enhanced workflows:

  • gdai-mcp-plugin-godot — semantic(0.59)+same_lang+similar_pop+shared_platform (51%)
  • Godot-MCP — semantic(0.47)+same_lang+similar_pop+shared_platform (47%)

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular GDScript Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools