medxpert-library-connector
Integrates with local Ollama for embedding wiki documents and generating answers in semantic search and RAG Q&A over a local knowledge base.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@medxpert-library-connectorSearch my wiki for backup and restore steps"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MedXpert 图书馆(通用版)连接器
把**你自己的 wiki(.md 文档)**做成可语义检索、可 RAG 问答的本地知识库 MCP 连接器。
纯 Python 标准库实现(stdio JSON-RPC 2.0),零第三方依赖
仅依赖本地 Ollama 做嵌入/生成,零积分、断网可用
知识库为你自有文档,连接器不绑定任何预置私有数据
全部计算在本机完成,不访问任何外部网络,不上传任何数据
工具
工具 | 说明 |
| 语义检索知识库,返回相关片段 + 相似度 |
| 读取单个 wiki 页全文 |
| 库范围:页数 / 分类 / 索引状态 |
| RAG 问答:检索 + 本地生成模型,附引用 |
Related MCP server: harness-health-engineering
快速开始
# 1. 安装并启动 Ollama,拉取模型
ollama pull bge-m3 # 检索必备(嵌入)
ollama pull qwen2.5:7b # 问答可选(生成)
# 2. 用你自己的文档替换 wiki/(本包自带 3 个示例页)
# 把 .md 放进 wiki/ 即可,可建子目录分类
# 3. 构建向量索引
python rag_engine.py build
# 4. 启动 MCP server(stdio)
python medxpert_library_server.py接入 WorkBuddy
包内 mcp.json 已提供标准配置;在开放平台或客户端中引用本包目录即可。
也可用环境变量覆盖默认行为:
变量 | 默认值 | 说明 |
| 本包 | 知识库目录(指向你的文档) |
|
| Ollama 地址 |
|
| 嵌入模型 |
|
| 生成模型(问答) |
包结构
medxpert-library-connector/
├── medxpert_library_server.py # MCP server(stdio,纯标准库)
├── rag_engine.py # 嵌入 / 余弦 / 构建 / 检索引擎
├── wiki/ # 示例知识库(替换成你自己的 .md)
├── connector-meta.json # 开放平台元数据
├── mcp.json # MCP 启动配置
├── icon.svg # 头像
├── LICENSE # MIT
├── requirements.txt # 依赖说明(仅 Ollama)
└── README.md合规与隐私
不内嵌受版权保护的标准正文,仅索引标准号与公开要点。
所有内容在本机处理,文档与查询均不上传外部服务。
知识库为使用者自有内容,发布者不对其内容负责。
Copyright (c) 2026 注册老炮 (Reg Lao Pao) — MIT License
权利与归属(Rights & Attribution)
MIT License © 注册老炮@MedXpert(代码)。
© 2026 赵兴华 / Steven Zhao·China (ORCID 0009-0001-0512-1237). All rights reserved.
名称状态 (name status) : "SynomosAI" / "MedXpert" — 未申请实体注册、未申请商标注册
(not a registered legal entity; no trademark registered)
mcp-name: io.github.zhaoxinghua09-cell/medxpert-library-connector
This server cannot be deployed
Maintenance
Related MCP Connectors
Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Personal context for every AI: search, read, and write back to your private Markdown library.
A cited wiki of your GitHub repo: search, read pages, find symbols and ask, with line citations.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides semantic search and a tag-based knowledge graph for any project, auto-discovering local markdown knowledge bases with YAML frontmatter.102 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables querying a local health knowledge base with hybrid RAG (vector + FTS5) and exploring backlinks between notes.MIT
- FlicenseAqualityDmaintenanceEnables indexing local documents (PDF, Markdown, text, code) into a knowledge base and querying them via semantic search using local embeddings, all running privately on your machine.4-
- FlicenseAqualityCmaintenanceEnables retrieval-augmented question answering over Obsidian vaults and document folders, with local embeddings, vector search, and cited source paths.7-