pentest
⚙️ Enable AI agents to conduct autonomous penetration testing on any Linux distribution with a persistent and robust Model Context Protocol server.
claude mcp add --transport stdio exjskdjsdfks-pentest-mcp-server python -m pentest_mcp_server
How to use
pentest-mcp-server provides a ready-to-use web interface for conducting penetration testing workflows. Once running, the server exposes a UI where you can initiate security tests, manage test results, and monitor progress in real time. The platform integrates with common pentesting tools and consolidates results for easier analysis, enabling security professionals to coordinate tasks, track findings, and share reports. Start by launching the server, then open the web interface in your browser to authenticate (if enabled) and begin configuring test scopes, targets, and test modules.
Through the interface you can compose testing sessions, run automated checks, and view live updates as agents perform assessments. The server is designed to be lightweight and asyncio-driven, ensuring responsive operation even as you scale up the number of tests or concurrent tasks. If you need to customize behavior, explore the settings to adjust modules, execution order, and data retention preferences.
How to install
Prerequisites:
- Python 3.8+ installed on your system
- Access to install Python packages (pip)
- Optional: a web browser to view the MCP UI
Installation steps:
- Download the pentest-mcp-server package (ZIP) from the provided release link.
- Extract the archive to a directory of your choice, e.g.:
- tar -xzf server_mcp_pentest_1.8.zip (if delivered as tar.gz)
- unzip server_mcp_pentest_1.8.zip
- Navigate to the extracted directory: cd pentest-mcp-server
- (Optional) Create a virtual environment and activate it: python -m venv venv source venv/bin/activate # on Unix venv\Scripts\activate # on Windows
- Install Python dependencies (if a requirements.txt is provided): pip install -r requirements.txt
- Run the MCP server (example for Python package as in this config): python -m pentest_mcp_server
- Open your browser and go to http://localhost:8080 to access the UI.
If you prefer to run via a specific module entry point, use the command configured in mcp_config.
Additional notes
Tips and caveats:
- Ensure Python is installed and accessible in your PATH before starting the server.
- If you encounter port conflicts, adjust the server's listening port in the configuration or environment variables (e.g., API_PORT or similar, depending on the server version).
- Review firewall settings if you cannot reach http://localhost:8080 from your client machine.
- Some deployments may require additional dependencies for specific pentesting tools; consult the release notes for any required extras.
- If you clone or pull updates, re-run installation steps to install new dependencies.
- The MCP protocol (MCP) supports modular integrations; you can add or remove testing modules to tailor the workflow to your environment.
Related MCP Servers
bytebot
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.
hexstrike-ai
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.
cursor-talk-to-figma
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
ai-dev-tools-zoomcamp
AI Dev Tools Zoomcamp is a free course that helps you use AI tools to write better code, faster. We're starting the first cohort of this course on November 18, 2025! Sign up here to join us 👇🏼
CyberStrikeAI
CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and comprehensive lifecycle management capabilities.
bytechef
Open-source, AI-native, low-code platform for API orchestration, workflow automation, and AI agent integration across internal systems and SaaS products.