byrdocs-search-mcp
Click on "Install 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., "@byrdocs-search-mcpsearch for probability theory past exam papers"
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.
byrdocs-search-mcp
北邮 byrdocs 资料库与历年真题的检索服务,以 Model Context Protocol 形式暴露,部署于 Cloudflare Workers。支持 MCP 的 AI 客户端接入后,即可检索教材、试卷、课程资料,以及新生生存指南与真题 wiki。
数据来自 byrdocs 国内镜像及其开源内容仓库。本服务仅建立检索索引并返回必要摘录,不分发原文文件。
工具
工具 | 用途 |
| 检索资料元信息(教材 / 试卷 / 课程资料),返回标题、课程、学年、文件类型、大小及下载链接 |
| 检索真题,按题 / 节返回题干、选项、答案、解析; |
| 检索生存指南,返回校园生活经验正文与出处,支持按校区 / 主题筛选 |
| 已弃用,仅作兼容保留,请改用上述工具 |
byrdocs 元数据不含上传时间;检索中的"学年"指试卷学年区间或教材出版年。查询关键词用于全文检索,筛选(类型、学年、阶段、学期等)请使用对应参数。
Related MCP server: doc-hub-mcp
数据来源
快照 | 内容 | 来源 |
| 资料元信息(教材 / 试卷 / 课程资料) | 镜像接口 |
| 真题按题 / 节切块,指南按节切块 | GitHub: |
| 构建时间与源仓 commit | 构建时生成 |
数据在构建时抓取并打包进 Worker,随部署一同发布。
架构
MCP 客户端 ──/mcp | /sse──▶ Cloudflare Worker(McpAgent / Durable Object)
首次请求:jieba-wasm 分词 + MiniSearch 建索引(内存,isolate 内复用)
数据:打包进 Worker 的 data/*.json无服务器,数据随代码部署,索引在运行时按需构建。
中文分词使用
jieba-wasm(Workers 环境不支持原生实现)。包体 gzip 约 3.3 MB,需 Cloudflare Workers 付费方案(脚本上限 10 MB)。
快速开始
npm install
npm run dev # 本地启动,默认 http://localhost:8787
npm run typecheck部署:
npx wrangler login
npm run deploy接入
Claude Desktop(claude_desktop_config.json,经 mcp-remote 桥接):
{
"mcpServers": {
"byrdocs-search": {
"command": "npx",
"args": ["mcp-remote", "https://<your-worker>.workers.dev/sse"]
}
}
}Cursor 等支持 HTTP MCP 的客户端可直接填写 https://<your-worker>.workers.dev/mcp。
鉴权(可选):设置环境变量 MCP_AUTH_TOKEN(wrangler secret 或 vars)后,/mcp 与 /sse 需携带 Authorization: Bearer <token>;/health 与 /version 不受限。
端点
路径 | 说明 |
| MCP Streamable HTTP |
| MCP SSE |
| 健康检查,返回索引条数 |
| 版本、构建时间、源仓 commit |
数据更新
npm run build-data # 重新抓取 metadata,并从 GitHub 源仓重建 knowledge
npm run deploy需可访问 GitHub。build-data 会将源仓更新至最新并记录 commit 至 data/build-info.json。
许可
检索逻辑源自 superdocs-agent。真题与指南内容版权归 byrdocs 及各源仓库(CC-BY-NC-SA 等)。本项目仅建立检索索引并返回必要摘录,不分发完整原文文件。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceIndexes local and enterprise documents to provide a unified personal knowledge base for AI clients via the Model Context Protocol. It supports full-text search across various file formats and integrates with platforms like Feishu and WeChat Work.Last updated39MIT
- Flicense-qualityDmaintenanceProvides retrieval of WeChat Work and Feishu developer documentation, enabling AI assistants to query API references without switching browsers.Last updated4119
- Alicense-qualityDmaintenanceEnables AI assistants to perform semantic, hybrid, and filtered search on indexed local documentation with RAG capabilities.Last updated2MIT
- Flicense-qualityDmaintenanceSearch and retrieve content from Get笔记 knowledge bases through natural language queries.Last updated
Related MCP Connectors
Search your knowledge bases from any AI assistant using hybrid RAG.
Search a billion+ documents — papers, books, code, legal cases, forums, Wikipedia, and more.
Agentic search over your Dewey document collections from any MCP-compatible client.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Jinchen-Yang/byrdocs-search-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server