loading…
Search for a command to run...
loading…
Enables querying an internal LightRAG knowledge base to retrieve technical documentation and structured information using hybrid search modes. It facilitates th
Enables querying an internal LightRAG knowledge base to retrieve technical documentation and structured information using hybrid search modes. It facilitates the integration of raw text or HTML results from a LightRAG server into LLM workflows.
A Model Context Protocol (MCP) server that provides a bridge to the LightRAG knowledge base. This allows AI assistants like Claude to query your technical documentation directly.
hybrid, naive, local, and global retrieval modes.python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
.env.example to .env and set:LIGHTRAG_URL: Your LightRAG backend URL.LIGHTRAG_LANG: Default language (zh or en).python lightrag_mcp.py
query_knowledge_basequery (string): Search query.mode (string): hybrid (default), naive, local, global.lang (string): zh (Traditional Chinese) or en (English).基於 Model Context Protocol (MCP) 的伺服器,作為 LightRAG 知識庫的橋樑。讓 AI 助手(如 Claude)可以直接查詢您的技術文件。
hybrid、naive、local 與 global 檢索模式。python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
.env.example 為 .env 並設定:LIGHTRAG_URL: LightRAG 後端 URL。LIGHTRAG_LANG: 預設語言 (zh 或 en)。python lightrag_mcp.py
query_knowledge_basequery (字串):查詢字句或問題。mode (字串):檢索模式,可選 hybrid (預設), naive, local, global。lang (字串):語言切換,可選 zh (正體中文) 或 en (英文)。See AGENTS.md for detailed guidelines. / 請參閱 AGENTS.md 了解詳細開發規範。
MIT
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"lightrag-mcp": {
"command": "npx",
"args": []
}
}
}