{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_sqktcdwue6sj","handle":"aigroup-rag-mcp","url":"https://wellknown.network/agents/aigroup-rag-mcp","links":{"self":"https://wellknown.network/agents/aigroup-rag-mcp/record.json","html":"https://wellknown.network/agents/aigroup-rag-mcp","markdown":"https://wellknown.network/agents/aigroup-rag-mcp/record.md","api":"https://wellknown.network/api/v1/agents/aigroup-rag-mcp","status":"https://wellknown.network/api/v1/agents/aigroup-rag-mcp/status","claim":"https://wellknown.network/agents/aigroup-rag-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/aigroup-rag-mcp/claim.json","badge":"https://wellknown.network/agents/aigroup-rag-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/aigroup-rag-mcp/history","tools":"https://wellknown.network/api/v1/agents/aigroup-rag-mcp/tools"},"ard":{"identifier":"urn:air::server:aigroup-rag-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"aigroup-rag-mcp","summary":"RAG知识库检索增强生成系统 - MCP服务器","description":"# RAG MCP Server - 智能知识库检索系统 \n \n<div align=\"center\"> \n \n[![Python](https://img.shields.io/badge/Python-3.10+-blue.svg)](https://www.python.org/) \n[![LlamaIndex](https://img.shields.io/badge/LlamaIndex-0.11+-green.svg)](https://www.llamaindex.ai/) \n[![MCP](https://img.shields.io/badge/MCP-1.0+-orange.svg)](https://modelcontextprotocol.io/) \n[![License](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) \n \n**基于 LlamaIndex + MCP 协议的企业级 RAG 知识库系统** \n \n支持多种检索模式 | 模块化架构 | HTTP/STDIO双传输 | 生产就绪 \n \n[功能特性](#-功能特性) • [快速开始](#-快速开始) • [架构设计](#️-架构设计) • [使用文档](#-使用文档) • [配置说明](#️-配置说明) \n \n</div> \n \n--- \n \n## 📋 目录 \n \n- [项目简介](#-项目简介) \n- [功能特性](#-功能特性) \n- [技术栈](#-技术栈) \n- [快速开始](#-快速开始) \n- [架构设计](#️-架构设计) \n- [使用文档](#-使用文档) \n- [配置说明](#️-配置说明) \n- [MCP服务器](#-mcp服务器) \n- [检索模式](#-检索模式) \n- [开发指南](#-开发指南) \n- [常见问题](#-常见问题) \n- [贡献指南](#-贡献指南) \n \n--- \n \n## 🎯 项目简介 \n \n**RAG MCP Server** 是一个基于 **LlamaIndex** 框架和 **MCP（Model Context Protocol）**协议的企业级检索增强生成（RAG）系统。该系统提供了强大的知识库管理和智能检索能力，支持多种检索模式，可通过 MCP 协议与 AI 助手（如 Claude Desktop）无缝集成。 \n \n### 核心优势 \n \n✅ **多模式检索**：支持向量检索、BM25检索和混合检索   \n✅ **模块化设计**：清晰的代码组织，易于维护和扩展   \n✅ **双传输支持**：STDIO 和 HTTP/SSE 两种传输方式   \n✅ **中文优化**：使用 jieba 分词，完美支持中文文档   \n✅ **生产就绪**：支持 Qdrant 云存储，可横向扩展   \n✅ **开发友好**：完整的日志系统和错误处理   \n \n--- \n \n## ✨ 功能特性 \n \n### 🔍 智能检索系统 \n \n- **向量检索（Vector Search）** \n  - 基于语义相似度的密集向量检索 \n  - 使用 SiliconFlow Embedding API \n  - 支持 Qwen3-Embedding-8B 等先进模型 \n   \n- **BM25检索（Sparse Retrieval）** \n  - 基于关键词匹配的稀疏检索 \n  - 使用 jieba 进行中文分词 \n  - 支持自定义停用词过滤 \n \n- **混合检索（Hybrid Search）** 🌟 \n  - 融合向量检索和BM25检索 \n  - 使用 QueryFusionRetriever 进行结果融合 \n  - 提供最佳的检索效果 \n \n### 📦 向量存储 \n \n- **本地存储（Simple Vector Store）** \n  - 轻量级本地文件存储 \n  - 适合开发和小规模部署 \n   \n- **Qdrant云存储** \n  - 支持 Qdrant 云向量数据库 \n  - 生产级性能和可靠性 \n  - 支持分布式部署 \n \n### 🔌 MCP协议支持 \n \n- **STDIO传输** \n  - 标准输入/输出流通信 \n  - 适合本地集成（如 Claude Desktop） \n   \n- **HTTP/SSE传输** \n  - 基于 FastAPI 的 HTTP 服务器 \n  - 支持 Server-Sent Events (SSE) \n  - 适合远程访问和微服务架构 \n \n### 🛠️ MCP工具集 \n \n| 工具名称 | 功能描述 | \n|---------|---------| \n| `build_in…","publisher":null,"homepage":"https://github.com/your-org/aigroup-rag-mcp/blob/main/README.md","repository":"https://github.com/your-org/aigroup-rag-mcp/blob/main/README.md","version":"1.2.1","license":"MIT","protocols":["mcp"],"tags":["rag","mcp","llamaindex","knowledge-base","ai","nlp"],"pricing":null,"endpoints":[{"url":"pypi:aigroup-rag-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"}],"categories":["data"],"language":"fr"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"aigroup-rag-mcp","registry":"pypi","observedAt":"2026-11-08T22:25:09.193Z","publishedAt":"2026-01-12T01:59:28.967218Z","latestVersion":"1.2.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"aigroup-rag-mcp","url":"https://pypi.org/project/aigroup-rag-mcp/","firstSeenAt":"2026-09-09T08:21:40.999Z","fetchedAt":"2026-11-08T22:24:12.511Z","normalizedAt":"2026-11-08T22:24:12.511Z"}]},"firstSeenAt":"2026-09-09T08:21:40.999Z","updatedAt":"2026-11-08T22:25:09.193Z"}