MCP ExplorerExplorer

Mcp Godot Rag

@weekitmoon 9 months ago
11 MIT
FreeCommunity
AI Systems
This MCP server is used to provide Godot documentation to the Godot RAG model.

Overview

What is Mcp Godot Rag

mcp_godot_rag is an MCP server designed to provide Godot documentation to the Godot RAG model, facilitating access to comprehensive information about Godot.

Use cases

Use cases for mcp_godot_rag include providing documentation support for developers working on Godot projects, enhancing learning experiences for students, and integrating Godot documentation into AI-driven applications.

How to use

To use mcp_godot_rag, set up the server by following the initiation steps outlined in the README, including cloning Godot documentation, converting formats, chunking files, and creating a vector database. Finally, start the MCP server with the appropriate command.

Key features

Key features of mcp_godot_rag include the ability to convert and chunk documentation, create a vector database for efficient querying, and support for multiple models such as all-MiniLM-L6-v2 and bge-m3.

Where to use

mcp_godot_rag can be used in software development environments, particularly those focused on game development with Godot, as well as in educational settings for teaching Godot.

Content

A MCP server for Godot RAG

This MCP server is used to provide Godot documentation to the Godot RAG model.

Screenshot

Before using

before

After using

after

MCP server config

{
  "mcpServers": {
    "godot-rag": {
      "command": "python",
      "args": [
        "<path to the server script 'main.py'>",
        "-d",
        "<path to the chroma_db on your computer>",
        "-c",
        "<name of the collection in the chroma_db>"
      ]
    }
  }
}

Setup

uv venv --python 3.12
source ./.venv/bin/activate
uv sync
cp .env.example .env.local

Initiation steps

# clone godot docs
python download_godot_docs.py
# convert rst to markdown
python convert_rst2md.py
# chunk markdown files
python chunker.py -i artifacts
# create vector database
python vectorizer.py -i artifacts/chunks/artifacts_chunks_SZ_400_O_20.jsonl
# python vectorizer_api.py -i artifacts/chunks/artifacts_chunks_SZ_400_O_20.jsonl -m BAAI/bge-m3
# start mcp server
python main.py -d artifacts/vector_stores/chroma_db -c artifacts_chunks_SZ_400_O_20_all-MiniLM-L6-v2
# python main_with_api.py -d artifacts/vector_stores/chroma_db -c artifacts_chunks_SZ_400_O_20_BAAI-bge-m3 -k <your openai api key>

Debug

npx @modelcontextprotocol/inspector \
  uv \
  --directory . \
  run \
  main.py \
  --chromadb-path artifacts/vector_stores/chroma_db \
  --collection-name artifacts_chunks_SZ_400_O_20_all-MiniLM-L6-v2

Use Another Model

Other

mcp_godot_rag is indexed and certified by MCP Review

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers