Comprehensive pentesting MCP server that orchestrates 80 security tools across reconnaissance, web scanning, injection testing, exploitation, Active Directory attacks, cloud security, and stealth operations. Features a safety pipeline with input sanitization, target allowlists, rate limiting, and audit logging. Includes 35 pre-built workflow prompts, 20 reference resources (OWASP Top 10, MITRE ATT&CK, PTES methodology), and tiered Docker images (minimal/core/full). Supports both interactive copilot mode via MCP and a fully autonomous agent mode using LangGraph that follows the 7-phase PTES methodology with human-in-the-loop gates for destructive actions.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.