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).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.