MCP Server RAG
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MCP Server RAG (Retrieval-Augmented Generation)
📖 项目简介
mcp-server-rag 是一个专为大语言模型与 AI 智能体(Claude Desktop、Antigravity、Cursor、Cline 等)设计的检索增强生成(RAG)MCP 服务端。通过标准化的 Model Context Protocol (MCP) 接口,为 Agent 提供知识库索引、文档切分、向量嵌入、混合检索与上下文注入能力。
Related MCP server: io.github.Brightdotdev/darwin-rag
✨ 核心特性
🚀 极速轻量:基于 FastMCP 与现代 Python 3.10+,启动秒级响应,资源占用低;
🛡️ 工程规范标准:完全继承 oss-template 工业级开源底座,集成 GitHub Actions CI/CD、代码质量门禁 (Ruff) 与 Git 原生提交守护钩子;
📦 全场景分发:支持 PyPI 官方包发布、多架构 Docker 镜像 (GHCR) 以及一键
uvx免安装即用;🧩 领域模型对齐:遵循严谨的统一领域语言规范(详见 CONTEXT.md)。
🛠️ 快速开始
方式一:使用 uvx 免安装直接运行 (推荐首选)
uvx atengk-mcp-server-rag方式二:使用 Docker 容器运行
docker run -i --rm ghcr.io/atengk/mcp-server-rag:latest或使用内置 docker-compose.yml:
docker compose up -d方式三:本地开发与源码安装
# 1. 克隆仓库
git clone https://github.com/atengk/mcp-server-rag.git
cd mcp-server-rag
# 2. 激活本地 Git 规范提交守护钩子
git config core.hooksPath .githooks
# 3. 使用 uv 安装依赖并启动环境
uv sync
# 4. 运行服务
uv run mcp-server-rag💻 MCP 客户端接入配置
在你的 MCP 客户端配置文件(如 Claude Desktop 的 claude_desktop_config.json 或 Antigravity MCP 配置文件)中追加如下配置:
{
"mcpServers": {
"rag": {
"command": "uvx",
"args": ["atengk-mcp-server-rag"]
}
}
}如需使用源码或本地虚拟环境启动:
{
"mcpServers": {
"rag": {
"command": "uv",
"args": ["run", "--directory", "/path/to/mcp-server-rag", "mcp-server-rag"]
}
}
}🧪 测试与质量验证
# 代码风格与静态分析检查
uv run ruff check .
uv run ruff format --check .
# 单元测试执行
uv run pytest📄 开源许可
本项目遵循 Apache-2.0 许可证。欢迎提交 Issue 与 Pull Request!
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
A second brain for your AI agent. Shared memory for your team's AI agents, plus public and private knowledge bases — works with ChatGPT, Claude, Cursor and any MCP client.
Ask your own documents and get answers that cite the source passage. Workspace knowledge bases over MCP for Cursor, Claude and any MCP client.
Your personal library, readable by AI agents: durable snapshots, hybrid search, 46 MCP tools.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables building production-grade RAG systems with agentic reasoning, hybrid retrieval, and MCP protocol integration for use with Claude Desktop.1MIT
- AlicenseNot gradedqualityCmaintenanceA local-first RAG engine that ingests documents (PDF, Markdown, images, etc.) and provides hybrid search, reranking, and LLM answer synthesis via MCP for AI agent integration.34 PyPI3MIT
- FlicenseNot gradedqualityDmaintenanceA fully local MCP server that imports Markdown, PDF, and web pages into a running knowledge base, providing hybrid search and document retrieval via authenticated Streamable HTTP for Codex and DeepSeek agents.-

fayna-rag-mcpofficial
AlicenseNot gradedqualityCmaintenanceEnables local knowledge base management with retrieval-augmented generation (RAG), providing semantic search, document reading, listing, and Q&A via MCP tools and REST endpoints, all running locally without cloud dependencies.MIT