kb-agent-platform
Enables MCP hosts like Cursor or Claude to query an enterprise knowledge base via stdio, providing RAG-based answers with cited sources.
README
KB-Agent-Platform —— 企业知识库问答平台(RAG + Multi-Agent + MCP)
一句话:基于 RAG 与 LangGraph Supervisor 的企业知识库 Agent, SSE 流式问答带引用溯源,MCP 双入口,docker compose 一键部署。
架构
前端 Vue3 ──SSE──> FastAPI ──> Supervisor(LLM 路由) ──┬─> KB Agent ──> Qdrant(4096维)
└─> Chat Agent
MCP Host(Cursor/Claude) ──stdio──> MCP Server ──> 同一个 Qdrant

快速开始
- git clone https://github.com/embracingTheFuture/kb-agent-platform.git && cd kb-agent-platform
- cp .env.example .env # 填入你的 key
- docker compose up --build -d
- docker compose run --rm api python task2_pipeline.py # 入库
- 打开 http://localhost:8000/docs
效果截图

质量:评估集回归
6 条用例覆盖路由正确性 + 引用完整性,容器内可复现。
| 编号 | 前15个字 | 预期 | 实际 | 是否通过测试 |
|---|---|---|---|---|
| 编号:1 | 前15个字:阶段二的时间安排和主项目定位。 | 预期:KB | 实际:KB | PASS |
| 编号:2 | 前15个字:路线图里 Day16 要干什么 | 预期:KB | 实际:KB | PASS |
| 编号:3 | 前15个字:用一句话介绍一下你自己。 | 预期:CHAT | 实际:CHAT | PASS |
| 编号:4 | 前15个字:帮我写一句关于秋天的诗。 | 预期:CHAT | 实际:CHAT | PASS |
| 编号:5 | 前15个字:2024年奥运会中国队拿了多少 | 预期:CHAT | 实际:CHAT | PASS |
| 编号:6 | 前15个字: | 预期:CHAT | 实际:CHAT | PASS |
| 6 条用例,6 通过,0 失败 |
技术要点
- 手写 ReAct 内核(工具注册表 + while 循环,不用框架)
- 自研切分-向量化-检索管线,Qdrant 余弦相似度
- 引用溯源:编号上下文 + [i] 标注 + citations 结构
- Supervisor 多智能体路由 + 会话记忆压缩(滚动摘要)
- MCP Server 双入口 / SSE 流式 / 评估集回归
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.