Back to Home
SafeBreach icon

safebreach-mcp

by SafeBreach

Overview

A Model Context Protocol (MCP) server that bridges AI agents with SafeBreach's Breach and Attack Simulation platform for natural language queries and seamless integration.

Installation

Run Command
safebreach-mcp-all-servers

Environment Variables

  • SAFEBREACH_MCP_ALLOW_EXTERNAL
  • SAFEBREACH_MCP_AUTH_TOKEN
  • SAFEBREACH_MCP_CONFIG_EXTERNAL
  • SAFEBREACH_MCP_DATA_EXTERNAL
  • SAFEBREACH_MCP_UTILITIES_EXTERNAL
  • SAFEBREACH_MCP_PLAYBOOK_EXTERNAL
  • SAFEBREACH_MCP_BIND_HOST
  • SAFEBREACH_ENVS_FILE
  • SAFEBREACH_LOCAL_ENV
  • DATA_URL
  • CONFIG_URL
  • SIEM_URL
  • ACCOUNT_ID
  • {console_name}_APITOKEN

Security Notes

The server's default configuration binds to localhost (127.0.0.1) and is secure. It uses robust practices for secret management (AWS SSM, Secrets Manager, environment variables) and explicitly warns against hardcoding secrets. There is no evidence of 'eval' or other dynamic code execution patterns. However, the documentation explicitly states that 'The current authorization method is experimental and does not contain validated authentication flows for external MCP connections.' This critical self-admission indicates potential vulnerabilities in its external authentication mechanism, even though a Bearer token is required for external access. Therefore, while safe for local development, external deployment is risky and not recommended for production or sensitive environments.

Similar Servers

Stats

Interest Score35
Security Score6
Cost ClassMedium
Avg Tokens2000
Stars5
Forks0
Last Update2025-12-06

Tags

AI Agent IntegrationSecurity Breach SimulationMulti-server ArchitectureAPI GatewayData Transformation