GitHub PR Analyzer MCP Server
Fetches GitHub pull request details and saves reviews to Notion.
README
GitHub PR Analyzer MCP Server
MCP server that fetches GitHub pull request details and saves reviews to Notion. Built with FastMCP (stdio transport) for clients like Claude Desktop.
Tools
| Tool | Description |
|---|---|
fetch_pr_changes |
Fetch PR metadata and file changes from GitHub |
create_notion_page |
Create a child page under a shared Notion parent page |
Setup
cd pr_reviewer
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
Or with uv:
uv venv && source .venv/bin/activate
uv pip install -r requirements.txt
Environment
Copy .env (do not commit secrets):
GITHUB_TOKEN=ghp_your_github_pat
NOTION_API_KEY=ntn_your_notion_integration_secret
NOTION_PAGE_ID=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
| Variable | Notes |
|---|---|
GITHUB_TOKEN |
GitHub PAT with access to the repos you want to review |
NOTION_API_KEY |
Internal integration secret from Notion integrations |
NOTION_PAGE_ID |
Parent page UUID (or page URL). New reviews are created under this page |
Notion: share the page
The parent page must be connected to your integration:
- Open the parent page in Notion
···→ Connect to / Add connections- Select your integration (e.g.
PR Review Server Demo)
Without this, Notion returns “Could not find page… shared with your integration”.
Run locally
python pr_analyzer.py
This starts an stdio MCP server and waits for a client. Prefer launching it from Claude Desktop rather than testing alone in a terminal.
Claude Desktop config
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"github_pr_analyzer": {
"command": "/ABS/PATH/TO/pr_reviewer/.venv/bin/python",
"args": ["/ABS/PATH/TO/pr_reviewer/pr_analyzer.py"],
"cwd": "/ABS/PATH/TO/pr_reviewer"
}
}
}
Quit Claude completely (Cmd+Q) and reopen after editing.
Example prompt
Use github_pr_analyzer:
1) fetch_pr_changes for owner / repo / PR number
2) create_notion_page with a short title and the review summary
Logs
tail -f ~/Library/Logs/Claude/mcp-server-github_pr_analyzer.log
Project layout
pr_reviewer/
├── pr_analyzer.py # MCP server + tools
├── github_integration.py # GitHub API helper
├── requirements.txt
├── .env # secrets (gitignored)
└── README.md
Notes
- Notion paragraph text is limited to 2000 characters; long content is split into multiple blocks.
- Keep
.envand.venvout of git (see.gitignore).
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。