MCP Godot Rag

🚀 Building an MCP Server for Godot RAG

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

📸 Screenshots

Before Use

After Use

📦 Installation

MCP Server Configuration

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

Environment Configuration

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

Initialization Steps

# Clone Godot documentation
python download_godot_docs.py
# Convert rst format to Markdown
python convert_rst2md.py
# Split Markdown files
python chunker.py -i artifacts
# Create a 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_BAAI-bge-m3.jsonl -m BAAI/bge-m3
# Start the 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>

🐞 Debugging

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

💡 Using Other Models

• all-MiniLM-L6-v2
• bge-m3
• bge-large-zh-v1.5