This MCP server integrates Get笔记 (GetBiji) knowledge bases with Claude Desktop, enabling AI-powered search and retrieval of stored information.
Core Tools:
AI-Enhanced Search (
knowledge_search): Perform deep, AI-processed searches that synthesize comprehensive answers from your knowledge base, with support for deep thinking mode, reference inclusion, and conversation history for follow-up questionsRaw Content Recall (
knowledge_recall): Quickly retrieve unprocessed original content without AI processing, with options for intent rewriting, result re-selection, top K filtering, and conversation contextRate Limit Monitoring (
get_rate_limit_stats): Check current API usage statistics for QPS (2 requests/second) and daily quota (5000 requests/day)
Key Features:
Automatic rate limit management with intelligent queuing
Flexible configuration via environment variables (API key, base URL, default knowledge base, timeout, logging level)
Multiple installation options (global, npx, local dependency)
Bearer token authentication for secure API access
Type-safe TypeScript implementation with comprehensive error handling and logging
Seamless Claude Desktop integration
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., "@Get笔记 MCP Serversearch for information about TypeScript best practices"
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.
Get笔记 MCP Server
<a name="english"></a>
English
Overview
A Model Context Protocol (MCP) server for integrating with Get笔记 (GetBiji) API, enabling AI-powered knowledge base search and retrieval capabilities.
Features
✅ MCP server framework with stdio transport
✅ Get笔记 API client with Bearer token authentication
✅ Rate limiting (2 QPS, 5000 requests/day)
✅ Comprehensive error handling and logging
✅ TypeScript with full type safety
✅ Three MCP tools:
knowledge_search: AI-enhanced knowledge base searchknowledge_recall: Raw content retrievalget_rate_limit_stats: Rate limit statistics
Installation
Option 1: Install globally (recommended for frequent use)
Option 2: Use with npx (no installation required)
Option 3: Install as project dependency
Configuration
Copy the environment template:
Edit
.envand add your API key:
Usage with Claude Desktop
Edit your Claude Desktop config file (~/Library/Application Support/Claude/claude_desktop_config.json):
Using global installation:
Using npx:
Using local installation:
Restart Claude Desktop to activate the server.
MCP Tools
1. knowledge_search
AI-enhanced search with deep processing, providing comprehensive answers based on your knowledge base.
Parameters:
question(required): Search querytopic_ids(optional): Knowledge base ID list (currently supports 1) - can be omitted if configured via GET_BIJI_DEFAULT_TOPIC_IDdeep_seek(required): Enable deep thinkingrefs(optional): Include referenceshistory(optional): Conversation history for follow-up
2. knowledge_recall
Fast retrieval of raw content without AI processing, useful for quick previews and raw data access.
Parameters:
question(required): Search querytopic_id(optional): Single knowledge base ID (preferred)topic_ids(optional): Knowledge base ID listtop_k(optional): Number of top results (default: 10)intent_rewrite(optional): Enable intent rewritingselect_matrix(optional): Enable result re-selectionhistory(optional): Conversation history
Note: Either topic_id or topic_ids can be omitted if configured via GET_BIJI_DEFAULT_TOPIC_ID. topic_id takes priority if both are provided.
3. get_rate_limit_stats
Get current API rate limit usage statistics.
Development
API Rate Limits
QPS: 2 requests/second
Daily: 5000 requests/day
The server automatically handles rate limiting with intelligent queuing.
Project Structure
Tech Stack
Node.js (ES Modules)
TypeScript
@modelcontextprotocol/sdk
Axios
dotenv
License
MIT
Contributing
Contributions welcome! Please open an issue or submit a pull request.
Special thanks to the contribution & development of Xiaoyibao-Pancrepal & xiao-x-bao community to support cancer/rare disease patients and their families with ❤️ & AI!
This project is proudly supported by the xiao-x-bao community, dedicated to helping cancer and rare disease patients and their families through AI technology and community support.
<a name="chinese"></a>
中文
项目概述
一个用于集成Get笔记API的Model Context Protocol (MCP)服务器,实现AI增强的知识库搜索和召回功能。
功能特性
✅ 基于stdio传输的MCP服务器框架
✅ 支持Bearer Token认证的Get笔记API客户端
✅ 速率限制 (2 QPS, 5000次/天)
✅ 完善的错误处理和日志记录
✅ TypeScript完整类型安全
✅ 三个MCP工具:
knowledge_search: AI增强知识库搜索knowledge_recall: 原始内容召回get_rate_limit_stats: 速率限制统计
安装
方式1: 全局安装 (推荐常用场景)
方式2: 使用 npx (无需安装)
方式3: 作为项目依赖安装
配置
复制环境变量模板:
编辑
.env文件,添加您的API密钥:
在Claude Desktop中使用
编辑Claude Desktop配置文件 (~/Library/Application Support/Claude/claude_desktop_config.json):
使用全局安装:
使用 npx:
使用本地安装:
重启Claude Desktop以激活服务器。
MCP工具说明
1. knowledge_search
AI增强搜索,返回经过深度处理的答案。
参数:
question(必填): 搜索问题topic_ids(必填): 知识库ID列表(当前只支持1个)deep_seek(必填): 启用深度思考refs(可选): 返回引用来源history(可选): 对话历史,用于追问
2. knowledge_recall
快速召回原始内容,不经过AI处理。
参数:
question(必填): 搜索问题topic_id(可选): 单个知识库ID(优先使用)topic_ids(可选): 知识库ID列表top_k(可选): 返回前N个结果(默认:10)intent_rewrite(可选): 启用意图重写select_matrix(可选): 启用结果重选history(可选): 对话历史
注意: topic_id 和 topic_ids 必须提供一个,优先使用 topic_id。
3. get_rate_limit_stats
获取当前API速率限制使用统计。
开发命令
API限制
QPS限制: 2次/秒
日限制: 5000次/天
服务器内置智能排队的速率限制器,自动处理这些限制。
项目结构
技术栈
Node.js (ES模块)
TypeScript
@modelcontextprotocol/sdk
Axios
dotenv
许可证
MIT
贡献
欢迎贡献!请提交 issue 或 pull request。
特别感谢小胰宝和 小x宝社区的贡献与付出,用爱心与人工智能为癌症/罕见病患者及其家庭提供支持!
🌟 小X宝公益社区
国内首个面向肿瘤/罕见病/慢性病的AI开源公益社区 AI技术赋能
专注AI+医疗公益应用
成功运营多个肿瘤AI助手(小胰宝、小肺宝等)
拥有丰富的患者服务经验