Mcp-Hydra

What is Mcp-Hydra?

Mcp-Hydra is a lightweight, extensible cybersecurity toolkit that connects AI assistants to security tools through the Model Context Protocol (MCP), enabling AI-assisted security research, scanning, and analysis. It is designed for security researchers and penetration testers who want to leverage AI for automated reconnaissance and vulnerability assessment.

How to use Mcp-Hydra?

Build the Docker image from the repository (git clone, docker build), then add the server configuration to your AI client’s MCP settings (e.g., claude_desktop_config.json for Claude Desktop, or .vscode/mcp.json for VS Code Copilot). The server runs inside a Docker container using the command docker run --rm -i --name hydramcp hydramcp.

Key features of Mcp-Hydra

• Connects AI assistants to eight pre-installed security tools
• Docker-based deployment for isolation and portability
• Supports Sublist3r, DNSRecon, Holehe, Nmap, OCR, Sqlmap, WPScan, and Zmap
• Lightweight and extensible with planned tool additions
• Provides example prompts for each integrated tool
• Open-source under the MIT license

Use cases of Mcp-Hydra

• Enumerate subdomains for a target domain using Sublist3r
• Perform DNS reconnaissance with DNSRecon
• Check if an email is registered on multiple websites via Holehe
• Scan a host for open ports using Nmap or a subnet for open ports with Zmap
• Automate SQL injection testing on web forms with Sqlmap

FAQ from Mcp-Hydra

What tools are included in Mcp-Hydra?

Mcp-Hydra currently includes Sublist3r, DNSRecon, Holehe, Nmap, OCR (optical character recognition), Sqlmap, WPScan, and Zmap.

How do I install Mcp-Hydra?

Clone the repository, then build the Docker image with docker build -t hydramcp .. No additional dependencies are required beyond Docker.

Which AI assistants are supported?

Mcp-Hydra works with any MCP-compatible client, such as Claude Desktop and VS Code Copilot, by configuring the server in their JSON settings.

Is Mcp-Hydra open source?

Yes, it is open-source under the MIT license, and contributions are welcome via forking and pull requests.

What are the planned future tools?

Planned tools include gobuster, TheHarvester, Shodan, Nuclei, Amass, and more, as listed in the project’s changelog.