enriquecatala/mcp-lightrag

开发工具

本页由 AI 翻译，技术细节请以原文为准。查看原文

8 stars 7 forks 质量 68 趋势 20Apache-2.0

Repository Install

the best mcp server for lightrag with support for idempotent uploads

概览

A Model Context Protocol (MCP) server that enables AI assistants to interact with LightRAG knowledge graphs. Query documents, manage entities, and build semantic relationships through a standardized tool interface. : The built-in smart upsert and document tracking capabilities make it perfect for agents that need to sync and reason over evolving Obsidian knowledge bases. - : Intelligent upsert logic that detects changes in documents, skipping redundant uploads and re-indexing only when necessary - : Perform semantic, keyword, or hybrid searches across your indexed documents - : Add text, files, or entire directories to your knowledge base - : Create, update, merge, and delete entities in the graph - : Define and modify connections between entities - : Automatic retry with exponential backoff for reliable API communication - : Set options via environment variables or command-line arguments 1. (must be running before the MCP server) 3.

README

以下为原文 README 节选，完整内容请查看原文。

LightRAG MCP Server

Features

Smart Updates: Intelligent upsert logic that detects changes in documents, skipping redundant uploads and re-indexing only when necessary
Knowledge Graph Queries: Perform semantic, keyword, or hybrid searches across your indexed documents
Document Ingestion: Add text, files, or entire directories to your knowledge base
Entity Management: Create, update, merge, and delete entities in the graph
Relationship Handling: Define and modify connections between entities
Robust Connectivity: Automatic retry with exponential backoff for reliable API communication
Flexible Configuration: Set options via environment variables or command-line arguments

Installation

# Clone the repository
git clone https://github.com/enriquecatala/mcp-lightrag.git
cd mcp-lightrag

# Install dependencies
uv sync

Quick Start

Start your LightRAG server (must be running before the MCP server)

Launch the MCP server:

uv run mcp-lightrag --host localhost --port 9621

Connect your AI assistant via the MCP protocol (stdio transport)

Configuration

Option	Environment Variable	Default	Description
`--host`	`LIGHTRAG_HOST`	`localhost`	LightRAG API host
`--port`	`LIGHTRAG_PORT`	`9621`	LightRAG API port
`--api-key`	`LIGHTRAG_API_KEY`	(none)	Optional API key
`--log-level`	—	`INFO`	Logging verbosity

Setting up as MCP Server

To integrate this server with an MCP client (such as Claude Desktop), add the following configuration to your mcp-server-config.json key in your settings file. This configuration uses uv to run the server from the source directory.

{
  "mcpServers": {
    "mcp-lightrag": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/mcp-lightrag",
        "run",
        "mcp-lightrag",
        "--host",
        "localhost",
        "--port",
        "9621"
      ],
      "env": {
        "LIGHTRAG_API_KEY": "optional_api_key"
      }
    }
  }
}

Note: Replace /absolute/path/to/mcp-lightrag with the actual full path to where you cloned this repository.

Smart Document Handling

在 GitHub 查看完整 README

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 →

配置

{
  "mcpServers": {
    "mcp-lightrag": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/mcp-lightrag",
        "run",
        "mcp-lightrag",
        "--host",
        "localhost",
        "--port",
        "9621"
      ],
      "env": {
        "LIGHTRAG_API_KEY": "optional_api_key"
      }
    }
  }
}