Second Brain MCP
A semantic search MCP server for codebases that uses OpenAI embeddings to understand natural language queries and find relevant code.
README
🧠 Second Brain MCP
Your code, but searchable like memories. Stop grepping, start remembering. A semantic search MCP server for your codebase—ask natural questions, get smart answers.
TL;DR
Second Brain MCP is a local server that indexes your code and other text-based files, allowing you to perform semantic searches using natural language. It runs as a Model Context Protocol (MCP) server, so you can interact with it from any MCP-compatible client. It uses OpenAI's embedding models to understand the meaning of your code, not just keywords.
🛠️ Tech Stack
This project is a TypeScript-based Node.js application.
| Component | Technology | Key Libraries/Frameworks |
|---|---|---|
| Application Runtime | Node.js | TypeScript, @modelcontextprotocol/sdk |
| Database | SQLite | better-sqlite3 |
| Embeddings | OpenAI | openai |
| Development | Package Manager | npm |
🚀 Quick Start
The following instructions are optimized for a Linux environment (Ubuntu/Debian).
Prerequisites
You must have Node.js (v20+) and npm installed.
-
Clone the repository
git clone https://github.com/RyanMaxiemus/second-brain-mcp.git cd second-brain-mcp -
Configure Environment Variables
You will need an OpenAI API key. You can set it as an environment variable:
export OPENAI_API_KEY="YOUR_OPENAI_API_KEY" -
Install Dependencies
Install all necessary Node.js dependencies.
npm install -
Build the Application
Compile the TypeScript code to JavaScript.
npm run build -
Run the Application
Launch the MCP server.
npm startThe server will be running and ready to accept connections from an MCP client.
🤝 Contributing
Found a bug? Have an idea for a new feature? We welcome all contributions!
- Open an Issue: Before submitting a Pull Request, please open an issue to discuss the bug or feature you're working on. This helps prevent duplicate work and ensures alignment with the project's goals.
- Fork and Branch: Fork the repository and create a new branch for your contribution.
- Code and Commit: Write clean, well-documented code. Commit messages should be descriptive and follow a conventional format (e.g.,
feat: add support for local embeddings). - Submit a PR: Submit a Pull Request against the
mainbranch. We'll review it as quickly as possible.
Let's make Second Brain the most intuitive code search tool available, together.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。