Github Second Brain

MCP开发工具

提供方 BaoNguyen09

开发工具 stdio · 本地进程 Token 社区 / 第三方 Claude DesktopClaudeCursorCline
查看接入方式

Providing tools to AI to explore github codebase like agent

一句话选型结论

按资料字段整理

Github Second Brain 属于开发工具类 MCP 服务器,stdio · 本地进程,Token,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类开发工具 传输方式stdio · 本地进程 鉴权Token 部署方式本地部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

开发工具
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

github ai mcp python3 fastapi second brain mcp server

支持客户端

适用场景

githubaimcp

安装与配置

stdio · 本地进程 Token
客户端在本机拉起子进程,数据不出本机
docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN ghcr.io/baonguyen09/github-second-brain:latest

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 python,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好Token对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Github Second Brain当前 未标注 stdio · 本地进程 本地部署 有 未标注
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
字段来自项目仓库与公开索引,中文说明由本站标注
提供方BaoNguyen09上游标注的维护方 BaoNguyen09
分类开发工具本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式Token远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · python本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

8.9 KB
来自项目仓库与上游目录的原文,未做删改

GitHub Second Brain

A set of tools that let AI explore github repos on-demand so it can better assist you.

Explore the docs »

Report Bug
Request Feature
Ask Question

Recent Major Update

This project underwent a major refactor in June 8th, 2025 (https://github.com/baonguyen09/github-second-brain/issues/42).

  • Legacy version: Available on legacy/v1-archive branch
  • Current version: Main branch (v2.0+)
  • Migration guide: See MIGRATION.md

Branch Information

  • main - Current refactored version
  • legacy/v1-archive - Original architecture (frozen)

Project Launch

Why?

The Problem

When I first started contributing to an open-source project to gain more experience, the repo was just too big for a first-timer, and I felt completely overwhelmed. I wanted to use an AI assistant to help me navigate, but I had no good way to provide the necessary context.

Solution

A self-hosted mcp server that gives an AI client a set of tools to explore and understand GitHub repos on its own.

✨ Features

  • 😎 Latest Documentation on ANY GitHub Project: Grant your AI assistant seamless access to the GitHub project's documentation and code. The built-in retrieval tools help the AI gets tree directory and specific file content without exceeding Context Window Limit!

  • 🧠 No More Hallucinations: With Github Second Brain, your AI assistant can provide accurate and relevant answers to your questions.

  • ✅ Open, Free, and Private: Github Second Brain is open-source and completely free to use. It doesn't collect personal information or store queries. This is completely self-hosted!

  • Extracting and analyzing data from GitHub repositories.

Getting Started

⚙️ Prerequisites

Before you begin, ensure you have met the following requirements:
1. To run the server in a container, you will need to have Docker installed.
2. Once Docker is installed, you will also need to ensure Docker is running. The image is public; if you get errors on pull, you may need to docker logout ghcr.io.
3. Lastly you will need to Create a GitHub Personal Access Token.
The MCP server can use many of the GitHub APIs, so enable the permissions that you feel comfortable granting your AI tools (to learn more about access tokens, please check out the documentation).

🚀 Installation

Usage with Claude Desktop

  1. In Claude Desktop, go to Settings > Developer > Edit Config
  2. Replace the configuration with:json { "mcpServers": { "github-second-brain": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/baonguyen09/github-second-brain:latest" ], "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_PERSONAL_GITHUB_ACCESS_TOKEN" } } } }

Usage with Cursor

Update your Cursor configuration file at ~/.cursor/mcp.json:json { "mcpServers": { "github-second-brain": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/baonguyen09/github-second-brain:latest" ], "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_PERSONAL_GITHUB_ACCESS_TOKEN" } } } }

⚙ How It Works

Github Second Brain connects your AI assistant to GitHub repositories using the Model Context Protocol (MCP), a standard that lets AI tools request additional information from external sources.
What happens when you use Github Second Brain:
1. You provide a docker image to your AI assistant that is used to build a local MCP server, exposing tools for fetching issue context, file content, directory tree, etc.
2. Prompt the AI assistant on documentation/code-related questions.
3. Your AI sends requests to the locally built MCP server to use its tools (with your approval).
4. Local server executes the AI's request and returns the requested data.
5. Your AI receives the information and generates a more accurate, grounded response without hallucinations.

🗺️ Roadmap

We are continuously working to improve GitHub Second Brain. Here are some of our planned features:

  • [x] ~~Add a mcp tool to retrieve file contents and tree directory with specified depth~~
  • [ ] Add a mcp tool to trieve ~~github issues~~ + pull request
  • [x] ~~Change the current gitingest processing to directly use github api for faster response~~
  • [x] ~~Change the architecture of the project to be completely self-hosted (data never leaves your machine)~~

For a more detailed view of our upcoming features and to suggest new ones, please see the open issues and our project board.

🤝 Contributing

Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

Non-technical ways to contribute

  • Give the project a star⭐!: This will help make the project better for you because it will increase the project reliability and visibility which attracts more contributor to improve this project.
  • Create an Issue: If you find a bug or have an idea for a new feature, please create an issue on GitHub. This will help us track and prioritize your request.
  • Spread the Word: If you like GitHub Second Brain, please share it with your friends, colleagues, and on social media. This will help us grow the community and make it even better.
  • Use GitHub Second Brain: The best feedback comes from real-world usage! If you encounter any issues or have ideas for improvement, please let us know by creating an issue on GitHub or by reaching out to Bao: thienbao05@arizona.edu .

Technical ways to contribute

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement".

  1. Fork the Project
  2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
  3. Commit your Changes (git commit -m 'Add some AmazingFeature')
  4. Push to the Branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

Please read our Contributing Guidelines for detailed instructions on how to contribute, our coding standards, and the pull request process. Also, please review our Code of Conduct to understand the community standards we uphold.

🛠️ Tools

Github Second Brain provides AI assistants with several valuable tools to help them access, understand, and query GitHub repositories.

get_processed_repo (deprecated)

  • This tool gives AI the entire codebase ingested into one prompt-friendly text file. It works by ingesting the entire codebase with gitingest library and serving it directly. This gives the AI a good comprehensive look of what the project is about. However, this tool isn't recommended and will soon be disabled because it can easily overflow AI with data, exceeding its Context Window Limit.

  • When it's useful: For small repos, and to ask any types of questions: overview of the repo, how to contribute, etc.

get_tree_directory

  • This tool gives AI the full tree directory of the codebase in plaintext with indentation. Instead of loading all the documentation (which could be very large), it can use this to understand the overview of the repo, and then use other tools to retrieve relevant parts only.

  • When it's useful: For questions about the structure of the repositories.

get_repo_contents

  • This tool returns full content of any files/directories existing in the repository.

  • When it's useful: For specific questions about particular features, functions, concepts within a project, or any technical details not coverted in the documentation.

get_issue_context

  • This tool returns detailed context of any github issues including title, body, metadata, and all the comments within that issue.

  • When it's useful: For questions related to a github issue and the context around it.

get_code_diff

  • This tool returns detailed diff of any github pull request, different branches, tags, and commits

  • When it's useful: For questions related to a github pull request or code versions (between branches/tags/releases)

📝 License

This project is licensed under the Apache License 2.0.

🙏 Acknowledgments

We would like to thank the following individuals and projects for their contributions and inspiration:

  • GitMCP for reference
  • Official GitHub MCP Server
  • All our amazing contributors!

Disclaimer

Github Second Brain is provided "as is" without warranty of any kind. While we strive to ensure the reliability and security of our service, we are not responsible for any damages or issues that may arise from its use. GitHub projects accessed through Github Second Brain are subject to their respective owners' terms and conditions. Github Second Brain is not affiliated with GitHub or any of the mentioned AI tools.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Github Second Brain 怎么安装?

在客户端按下面的安装命令接入:docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN ghcr.io/baonguyen09/github-second-brain:latest。装完在客户端配置里引用同一个包或端点。

Github Second Brain 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Github Second Brain 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Github Second Brain 需要 API Key 吗?

资料标注需要Token认证,使用前准备好对应凭据,并按最小权限配置。

Github Second Brain 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、Cline、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Github Second Brain 能提供哪些能力?

资料显示能力标签包括 github、ai、mcp、python3、fastapi、second brain。具体工具清单以官方文档为准。

Github Second Brain 需要什么运行环境?

运行时为 python;属于本地进程,需要在本机装好运行环境。

Github Second Brain 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。