GHOSTCREW – AI-based Red Team Toolkit for Penetration Testing Invoking Metasploit, Nmap and Other Tools
GHOSTCREW is an open-source toolkit designed for red teamers and penetration testers. This AI-driven assistant utilizes large language models and integrates the MCP protocol, with optional RAG architecture support, to manage security tools through…
GHOSTCREW is an open-source toolkit designed for red teamers and penetration testers. This AI-driven assistant utilizes large language models and integrates the MCP protocol, with optional RAG architecture support, to manage security tools through natural-language prompts.
Developed by GH05TCREW, the toolkit has gained significant interest in the cybersecurity community, evidenced by over 450 stars on GitHub. It features autonomous agent modes, predefined workflows, and markdown report generation to streamline the penetration testing process from reconnaissance to exploitation.
GHOSTCREW enables natural language interaction, facilitating network queries and scan launches while maintaining a multi-turn dialogue history.
The toolkit manages MCP servers via an interactive menu, allowing seamless configuration of tools stored in mcp.json. Advanced capabilities include Pentesting Task Trees (PTT) for dynamic decision-making in agent mode, streaming responses, and file-aware integration for accessing wordlists or payloads from a local knowledge directory.
Users have the option to enhance replies with RAG for precise, context-aware responses and configurable LLM parameters, with GPT-4o as the default via the OpenAI API.
GHOSTCREW is an open-source toolkit designed for red teamers and penetration testers.
GHOSTCREW connects to 18 MCP-compatible tools for comprehensive assessments:
Nmap: Network discovery and auditing Metasploit: Exploit execution and payloads FFUF: Web fuzzing SQLMap: SQL injection exploitation Nuclei: Vulnerability scanning Hydra: Brute-force attacks Masscan: High-speed port scanning
Additional tools such as Amass, Katana, and Scout Suite provide subdomain enumeration, crawling, and cloud audits. Future integrations include BloodHound and Gobuster.
Installation involves cloning the repository at github.com/GH05TCREW/ghostcrew , creating a virtual environment, and installing requirements via pip. Node.js and uv are required for full tool support; however, chat mode functions without them.
To launch, execute python main.py , configure MCP tools at startup, and select chat, workflow, or agent modes. Use the 'multi' command for multi-line inputs and 'quit' to exit.
This toolkit facilitates bug bounty hunting and threat analysis by automating workflows and generating structured reports with findings and recommendations. As AI agents advance, GHOSTCREW enhances the efficiency of penetration testing operations, combining human intuition with machine precision in black-box testing scenarios.
Based on reporting by Cyber Security News.