zivshek/rag-mcp 是从 https://github.com/zivshek/rag-mcp. 导入的 MCP 服务器候选
概览
zivshek/rag-mcp 是从 https://github.com/zivshek/rag-mcp. 导入的 MCP 服务器候选
概述(AI 翻译)
一个模型上下文协议(MCP)工具,可从本地 ChromaDB 数据库中获取关于 Godot 游戏引擎的相关信息。
虽然该工具专门针对Godot,但只需对工具描述做些许修改,它就可以用于任何Chroma数据库。
用途
- 使用web2embeddings工具准备好chroma_db向量存储。
- 将该仓库下载或克隆到你的本地磁盘。
- 在VSCode Insiders中配置MCP服务器(见下文配置说明)。
Visual Studio Code Insiders 配置
NOTE: 你可能需要下载 Visual Studio Code Insiders 版本以使用 MCP 或代理模式。
系统配置为 settings.json:
本页由 AI 翻译,技术细节请以原文为准。
README
Godot RAG MCP
A Model Context Protocol (MCP) tool that retrieves relevant information about Godot game engine from a local ChromaDB database.
Although this tool is for Godot in particular, but with small changes to the tool description, it can be used for any chroma database.
Usage
- Get the chroma_db vector store ready using the web2embeddings tool.
- Download or clone this repository to your local disk.
- Configure the MCP server in VSCode Insiders (see below config instructions).
Configuration with Visual Studio Code Insiders
NOTE: You may need to download Visual Studio Code Insiders version to use MCP or Agent mode.
The system is configured through settings.json:
"mcp": {
"inputs": [],
"servers": {
"godot_rag": { // or whatever name you want
"command": "cmd", // replace this with "uv" on Mac or Linux
"args": [
"/c", // remove this on Mac or Linux
"uv", // remove this on Mac or Linux
"run",
"path to the server script 'server.py'", // C:\\dev\\rag-mcp\\server.py
"-d",
"path to the chroma_db on your computer", // C:\\dev\\web2embeddings\\artifacts\\vector_stores\\chroma_db
"-c",
"name of the collection in the chroma_db" // godotengine_chunks_SZ_400_O_20_all-MiniLM-L6-v2
]
}
}
}
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手?先看 mcpskill.org 教程 →