AI for Ethical Hacking
AI for Ethical Hacking - Workshop
What is AI for Ethical Hacking?
AI for Ethical Hacking is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai for ethical hacking - workshop
AI for Ethical Hacking - Workshop
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- AI for Ethical Hacking - Workshop
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ai4ehConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AI for Ethical Hacking
AI for Ethical Hacking (AI4EH) is a Python-based workshop toolkit that integrates large language models with a suite of offensive security tools for learning and practicing ethical hacking techniques. It wraps tools like Subfinder, PureDNS, Nuclei, HTTPx, and FFUF inside an LLM-driven workflow, enabling AI-assisted subdomain enumeration, vulnerability scanning, screenshot classification with multimodal models, and custom fuzzing wordlist generation. The workshop uses Docker for a consistent, isolated environment and requires OpenAI and Gemini API keys to power the AI reasoning layer.
Prerequisites
- Docker and Docker Compose installed
- An OpenAI API key (OPENAI_API_KEY) for LLM reasoning
- A Google Gemini API key (GEMINI_API_KEY) for multimodal screenshot analysis
- An MCP client such as Claude Desktop (if using the MCP interface)
- Permission to test only systems you own or have explicit written authorization for
Clone the repository
Clone the AI4EH workshop repository from GitHub.
git clone https://github.com/ethiack/ai4eh.git
cd ai4ehCreate an environment variables file
Create an env_file in the project root with your API keys.
OPENAI_API_KEY=your_openai_api_key_here
GEMINI_API_KEY=your_gemini_api_key_hereBuild the Docker image
Build the AI4EH Docker image using the provided build script.
chmod +x build_image.sh
./build_image.shRun the container
Start the AI4EH container using the provided run script, which loads your environment variables and launches the workshop environment.
chmod +x run_image.sh
./run_image.shAlternatively, use the pre-built image
If you prefer not to build locally, pull and run the pre-built Docker image directly from Docker Hub.
docker run --rm -it --env-file env_file ethiack/ai4eh:latestConfigure Claude Desktop for MCP integration
To use AI4EH as an MCP server within Claude Desktop, add it to your MCP config pointing to the running container or the npx shim.
{
"mcpServers": {
"ai4eh": {
"command": "npx",
"args": ["ai4eh"],
"env": {
"OPENAI_API_KEY": "your_openai_api_key_here",
"GEMINI_API_KEY": "your_gemini_api_key_here"
}
}
}
}AI for Ethical Hacking Examples
Client configuration
Claude Desktop configuration block for the AI4EH MCP server with the required API key environment variables.
{
"mcpServers": {
"ai4eh": {
"command": "npx",
"args": ["ai4eh"],
"env": {
"OPENAI_API_KEY": "your_openai_api_key_here",
"GEMINI_API_KEY": "your_gemini_api_key_here"
}
}
}
}Prompts to try
Use these prompts when the AI4EH toolkit is active. Only test against systems you own or have explicit authorization to test.
- "Enumerate subdomains for example.com using Subfinder."
- "Run Nuclei against https://testsite.example.com and summarize vulnerabilities found."
- "Generate a custom fuzzing wordlist for an e-commerce login page."
- "Classify the screenshots in /scans/screenshots and identify which ones show login panels."
- "Run HTTPx against this list of hosts and show which ones respond on port 8080."Troubleshooting AI for Ethical Hacking
Docker build fails with permission errors on build_image.sh
Run `chmod +x build_image.sh run_image.sh` before executing the scripts, or prefix with `bash build_image.sh` to bypass the execute permission requirement.
LLM calls fail with API authentication errors
Verify that OPENAI_API_KEY and GEMINI_API_KEY are correctly set in your env_file. Ensure the file is in the same directory from which you run the docker command, and that the --env-file flag points to it.
Tools like Subfinder or Nuclei produce no results
Confirm the target domain is reachable from within the Docker container. DNS-dependent tools like PureDNS may need resolvers configured inside the container; check the workshop's resolver configuration files.
Frequently Asked Questions about AI for Ethical Hacking
What is AI for Ethical Hacking?
AI for Ethical Hacking is a Model Context Protocol (MCP) server that ai for ethical hacking - workshop It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AI for Ethical Hacking?
Follow the installation instructions on the AI for Ethical Hacking GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with AI for Ethical Hacking?
AI for Ethical Hacking works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AI for Ethical Hacking free to use?
Yes, AI for Ethical Hacking is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
AI for Ethical Hacking Alternatives — Similar Security Servers
Looking for alternatives to AI for Ethical Hacking? Here are other popular security servers you can use with Claude, Cursor, and VS Code.
Casdoor
★ 13.6kAn open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD
ghidraMCP
★ 9.0kAn Model Context Protocol server that enables LLMs to autonomously reverse engineer applications by exposing Ghidra's decompilation and analysis tools. It allows AI agents to list code structures, rename methods, and analyze binaries directly through
HexStrike AI
★ 8.9kHexStrike 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 b
IDA Pro MCP
★ 8.7kEnables AI-assisted reverse engineering in IDA Pro by providing tools to analyze binaries, decompile functions, manage comments, search patterns, and interact with the IDA database through natural language.
Anthropic Cybersecurity Skills
★ 6.6k754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platform
Hooker
★ 5.1k🔥🔥 hooker is a Frida-based reverse engineering toolkit for Android. It offers a user-friendly CLI, universal scripts, auto hook generation, memory roaming to detect activities/services, one-click SOCKS5 proxy setup, Frida JustTrustMe, and BoringSSL u
Browse More Security MCP Servers
Explore all security servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up AI for Ethical Hacking in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use AI for Ethical Hacking?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.