Sandbox
@MorDavid/ExternalAttacker-MCP

MCP server for attack surface scanning

This project exposes external attack surface management workflows through MCP. It uses a Python server plus ProjectDiscovery and fuzzing tools to handle requests such as subdomain discovery, port scans, HTTP analysis, CDN checks, TLS checks, DNS enumeration, and directory fuzzing.

78 starsβ€’17 forksβ€’Pythonβ€’Updated 1y ago
Who it's for

Builders who want an MCP-capable agent to run reconnaissance and vulnerability checks from natural language.

What it delivers

You can ask your agent to scan a target without manually stitching together the underlying security tools.

What it does

Natural language scan requests

You can ask for tasks like subdomain discovery, port checks, HTTP analysis, CDN detection, TLS inspection, and fuzzing in plain English.

MCP server integration

The server plugs into an MCP client so an agent can call the attack surface workflows as tools.

External reconnaissance toolchain

The README lists support for subfinder, naabu, httpx, cdncheck, tlsx, ffuf, gobuster, and dnsx.

Local web app

`ExternalAttacker-App.py` starts a local interface on `http://localhost:6991`.

How to get it

  1. 1Clone this repository
    git clone https://github.com/mordavid/ExternalAttacker-MCP.git
    cd ExternalAttacker
  2. 2Install Python dependencies
    pip install -r requirements.txt
  3. 3Run ExternalAttacker-App.py
    python ExternalAttacker-App.py
    # Access http://localhost:6991
  4. 4Configure the MCP Server
    "mcpServers": {
        "ExternalAttacker-MCP": {
            "command": "python",
            "args": [
                "<Your_Path>\\ExternalAttacker-MCP.py"
            ]
        }
    }

README

ExternalAttacker MCP Server

ExternalAttacker-MCP

Model Context Protocol (MCP) Server for External Attack Surface Management

ExternalAttacker is a powerful integration that brings automated scanning capabilities with natural language interface for comprehensive external attack surface management and reconnaissance.

πŸ” Automated Attack Surface Management with AI!
Scan domains, analyze infrastructure, and discover vulnerabilities using natural language.

πŸ” What is ExternalAttacker?

ExternalAttacker combines the power of:

  • Automated Scanning: Comprehensive toolset for external reconnaissance
  • Model Context Protocol (MCP): An open protocol for creating custom AI tools
  • Natural Language Processing: Convert plain English queries into scanning commands

πŸ“± Community

Join our Telegram channel for updates, tips, and discussion:

✨ Features

  • Natural Language Interface: Run scans using plain English
  • Comprehensive Scanning Categories:
    • 🌐 Subdomain Discovery (subfinder)
    • πŸ”’ Port Scanning (naabu)
    • 🌍 HTTP Analysis (httpx)
    • πŸ›‘οΈ CDN Detection (cdncheck)
    • πŸ” TLS Analysis (tlsx)
    • πŸ“ Directory Fuzzing (ffuf, gobuster)
    • πŸ“ DNS Enumeration (dnsx)

πŸ“‹ Prerequisites

  • Python 3.8 or higher
  • Go (for installing tools)
  • MCP Client

πŸ”§ Installation

  1. Clone this repository:

    git clone https://github.com/mordavid/ExternalAttacker-MCP.git
    cd ExternalAttacker
    
  2. Install Python dependencies:

    pip install -r requirements.txt
    
  3. Install required Go tools:

    go install -v github.com/projectdiscovery/subfinder/v2/cmd/subfinder@latest
    go install -v github.com/projectdiscovery/naabu/v2/cmd/naabu@latest
    go install -v github.com/projectdiscovery/httpx/cmd/httpx@latest
    go install -v github.com/projectdiscovery/cdncheck/cmd/cdncheck@latest
    go install -v github.com/projectdiscovery/tlsx/cmd/tlsx@latest
    go install -v github.com/ffuf/ffuf@latest
    go install github.com/OJ/gobuster/v3@latest
    go install -v github.com/projectdiscovery/dnsx/cmd/dnsx@latest
    
  4. Run ExternalAttacker-App.py

    python ExternalAttacker-App.py
    # Access http://localhost:6991
    
  5. Configure the MCP Server

    "mcpServers": {
        "ExternalAttacker-MCP": {
            "command": "python",
            "args": [
                "<Your_Path>\\ExternalAttacker-MCP.py"
            ]
        }
    }
    

πŸš€ Usage

Example queries you can ask through the MCP:

  • "Scan example.com for subdomains"
  • "Check open ports on 192.168.1.1"
  • "Analyze HTTP services on test.com"
  • "Check if domain.com uses a CDN"
  • "Analyze SSL configuration of site.com"
  • "Fuzz endpoints on target.com"

πŸ“œ License

MIT License

πŸ™ Acknowledgments

  • The ProjectDiscovery team for their excellent security tools
  • The MCP community for advancing AI-powered tooling

Note: This is a security tool. Please use responsibly and only on systems you have permission to test.

Files in the repo

Repository payloadβ€’9 top-level entries
  • .github
  • images
  • templates
  • .gitattributes
  • ExternalAttacker-App.py
  • ExternalAttacker-MCP.py
  • README.md
  • requirements.txt
  • version.txt

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph β€” average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code β€” use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300Β΅s in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up β€” it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k