F
licenseNot graded
qualityA
maintenanceExposes a compiled Markdown knowledge base to any MCP-capable coding agent through a single ask tool, returning cited answers grounded in full wiki articles over stdio or streamable HTTP.
-
kb-agent-platform
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
Related MCP server: KaaS
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
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
This server cannot be deployed
Maintenance
ActivityStale
ResponsivenessNo issues
Related MCP Connectors
Query any docs site via MCP. Submit a URL, ask questions, get cited answers.
- docs2mcpOAuthcom.docs2mcp
Query your own PDFs and documents from any MCP client. Every answer cites the page it came from.
Query SEC EDGAR filings, XBRL financials, and company data via MCP. STDIO or Streamable HTTP.
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceExposes a compiled Markdown knowledge wiki to any MCP-capable client through a single ask tool that returns cited Markdown answers grounded in whole wiki articles, available over stdio or an authenticated streamable-HTTP endpoint.-
- FlicenseNot gradedqualityAmaintenanceGives MCP-capable coding agents a single ask tool that returns cited Markdown answers grounded in a compiled wiki of the user's notes, docs, and transcripts. Runs locally over stdio or remotely as a streamable-HTTP endpoint at /mcp with optional bearer-token auth.-
- FlicenseNot gradedqualityAmaintenanceEnables MCP clients to query a compiled Markdown knowledge base through a single ask tool, returning cited answers grounded in wiki articles over stdio or streamable HTTP.-