SafeBreach MCP Server - Bridge AI agents with SafeBreach's Breach and Attack Simulation platform
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"iflow-mcp-safebreach-safebreach-mcp-server","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Disclaimer This is an experimental project intended to demonstrate SafeBreach capabilities with MCP. It is not officially supported or verified by SafeBreach. # SafeBreach MCP Server [](https://www.python.org/downloads/) [](LICENSE) [](https://safebreach.com) A Model Context Protocol (MCP) server that bridges AI agents with SafeBreach's Breach and Attack Simulation platform. Enables natural language queries and seamless integration through a multi-server architecture with specialized domains. ## 🚀 Quick Start ### New Team Members ```bash # 1. Clone and setup security tools (one-time setup) git clone <repository-url> cd safebreach-mcp ./setup-security.sh # 2. Configure your environment cp .env.template .env # Edit .env with your actual API tokens # 3. ALWAYS launch Claude with security context ./claude-launcher.sh ``` ### 🔒 Security-First Development This project implements comprehensive security measures to prevent API token leaks: - **Automated secret scanning** with pre-commit hooks - **Claude security context** ensuring AI awareness of best practices - **Template-based configuration** preventing accidental commits - **Multi-layer validation** in CI/CD pipelines 📚 **See [TEAM_WORKFLOW.md](TEAM_WORKFLOW.md) for complete development guidelines.** ## Table of Contents - [Overview](#overview) - [Features](#features) - [Architecture](#architecture) - [Configuration](#configuration) - [Installation](#installation) - [External Connection Support](#external-connection-support) - [Usage](#usage-) - [Registering with Claude Desktop](#registering-with-claude-desktop-) - [Windows Configuration](#windows-configuration) - [API Reference](#api-reference-) - [Testing](#testing-) - [Development](#development-) - [Troubleshooti…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.