mcp-gh-pr-mini
A minimal MCP (Model Context Protocol) server for interacting with GitHub pull requests.
y-hirakaw
README
mcp-gh-pr-mini
A minimal MCP (Model Context Protocol) server for interacting with GitHub pull requests.
This tool allows you to create, list, view diffs, request reviewers, and comment on pull requests in GitHub repositories via MCP.
✨ Features
- Create a pull request in a GitHub repository
- List open pull requests
- Get the diff for a pull request
- Request reviewers for a pull request
- Add a comment to a pull request
- Comments are automatically prefixed with "[AI] Generated using MCP" for clear identification
- Supports both general PR comments and position-specific code review comments
- Get comments from a pull request
- Get file changes with comment positions
- Retrieves detailed information about changed files
- Provides positions for adding review comments
- Shows additions, deletions, and patch information for each file
🛠️ Setup
This tool runs as an MCP server in your local environment. You can use it with tools like Copilot Agent or any MCP-compatible client.
Requirements
- Node.js installed
- VSCode with an MCP-compatible extension (e.g., Copilot Agent)
Configure in settings.json
In your VSCode settings.json
, add the following:
"mcp": {
"servers": {
"mcp-gh-pr-mini": {
"command": "npx",
"args": ["mcp-gh-pr-mini"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "{Your Fine-Grained GitHub Token}"
}
}
}
}
🔐 Token Permissions
💡 Use a fine-grained GitHub personal access token with the following permissions:
- Pull requests: Read and write
- Issues: Read and write
- Contents: Read and write
🤔 Why?
This project provides a minimal, focused implementation for essential pull request tasks via MCP. It's designed to be simple and easy to understand, making it a good reference for building MCP servers.
🙏 Note
I'm still new to building MCP servers, so there may be areas that can be improved. Feedback, suggestions, and contributions are always welcome!
推荐服务器
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。
MCP Package Docs Server
促进大型语言模型高效访问和获取 Go、Python 和 NPM 包的结构化文档,通过多语言支持和性能优化来增强软件开发。
Claude Code MCP
一个实现了 Claude Code 作为模型上下文协议(Model Context Protocol, MCP)服务器的方案,它可以通过标准化的 MCP 接口来使用 Claude 的软件工程能力(代码生成、编辑、审查和文件操作)。
@kazuph/mcp-taskmanager
用于任务管理的模型上下文协议服务器。它允许 Claude Desktop(或任何 MCP 客户端)在基于队列的系统中管理和执行任务。
mermaid-mcp-server
一个模型上下文协议 (MCP) 服务器,用于将 Mermaid 图表转换为 PNG 图像。
Jira-Context-MCP
MCP 服务器向 AI 编码助手(如 Cursor)提供 Jira 工单信息。

Linear MCP Server
一个模型上下文协议(Model Context Protocol)服务器,它与 Linear 的问题跟踪系统集成,允许大型语言模型(LLM)通过自然语言交互来创建、更新、搜索和评论 Linear 问题。

Sequential Thinking MCP Server
这个服务器通过将复杂问题分解为顺序步骤来促进结构化的问题解决,支持修订,并通过完整的 MCP 集成来实现多条解决方案路径。
Curri MCP Server
通过管理文本笔记、提供笔记创建工具以及使用结构化提示生成摘要,从而实现与 Curri API 的交互。