Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-github-paarths-collab-github-pr-context-mcp": {
"args": [
"github-pr-engine"
],
"command": "uvx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
This repository provides two ways to leverage your GitHub PR history in your AI workflows. Choose the tool version that matches your architecture.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
uvx 'github-pr-engine' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked github-pr-engine against OSV.dev.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in developer-tools / security
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
MCP server for accessing Figma plugin console logs and screenshots via Cloudflare Workers or local mode
MCP server for using the GitLab API
MCP Security Weekly
Get CVE alerts and security updates for io.github.paarths-collab/github-pr-context-mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
This repository provides two ways to leverage your GitHub PR history in your AI workflows. Choose the tool version that matches your architecture.
The Hardened Pure Context Retrieval Engine.
Designed for users who want maximum speed and reliability by offloading reasoning to their IDE agent (Cursor, Claude Desktop, Windsurf). It focuses exclusively on high-performance retrieval and data pruning.
tenacity retries and non-blocking I/O for heavy repository indexing.[!NOTE] v0.3.0 is currently in pre-release and is not yet live on PyPI. To use the hardened v0.3.0 engine today, you must install it from source:
Fork this repository to your own account on GitHub.
Clone and Checkout the release branch:
git clone https://github.com/YOUR_USERNAME/github-pr-context-mcp.git cd github-pr-context-mcp git checkout v0.3.0-hardeningInstall via pipx (the whole command):
pipx install -e .This links the
github-pr-context-mcpcommand to your local repository folder.Verify Version:
github-pr-context-mcp --help
The Integrated Reasoning Agent.
Designed for users who prefer the server to handle LLM inference internally. This version includes the legacy inference layer and supports direct configuration of OpenAI and Anthropic API keys.
inference/ module for direct model interactions.pipx install github-pr-context-mcp==0.2.9
The v0.3.0 version only requires a GitHub Token.
Environment Variable:
GITHUB_TOKEN=ghp_your_token_here
GitHub PR Review Context MCP gives AI assistants institutional review memory.
It fetches your repository's PR history (descriptions, review threads, comments), transforms them into searchable documents, and provides high-density Context Materials to your IDE agent.
| Capability | What It Delivers |
|---|---|
| Historical Retrieval | Semantic search across prior PR comments and review summaries. |
| Code Review Material | Raw JSON context for the agent to perform grounded code reviews. |
| Rules Material | High-density data for the agent to synthesize .cursorrules or CLAUDE.md. |
| Grounded Generation | Context materials for generating code that matches team style. |
| Namespace Isolation | Strict isolation between users/teams using Gmail-based identity. |