PatrikFehrenbach/h1-brain
MCP server that connects AI assistants to HackerOne for bug bounty hunting
What it solves
This project provides an intelligent interface for bug bounty hunters to integrate their HackerOne activity with AI assistants. It automates the process of gathering program scopes, analyzing personal past performance, and cross-referencing public vulnerability data to generate actionable attack briefings.
How it works
It functions as an MCP (Model Context Protocol) server that connects AI clients like Claude Desktop or Claude Code to the HackerOne API and local SQLite databases. It maintains two primary data sources: a personal database containing your specific report history and program activity, and a pre-built database of over 3,600 publicly disclosed bounty reports. When the hack(handle) tool is invoked, the AI synthesizes this data to identify untouched assets and suggest specific attack vectors based on historical patterns.
Who it’s for
This tool is designed for security researchers and bug bounty hunters who use AI assistants to streamline their reconnaissance and vulnerability research workflows.
Highlights
- Automated Briefings: The
hack()tool generates comprehensive attack plans by combining personal history with community-sourced vulnerability data. - Dual-Database Analysis: Separates private research data from public disclosure knowledge to provide context-aware suggestions.
- MCP Integration: Seamlessly plugs into standard AI interfaces like Claude Desktop for direct interaction.
- Offline-Ready: Includes a pre-populated database of 3,600+ public reports for immediate analysis without needing external API calls for community data.
Related
- Project
- Project
- Project
- Project