pentestMCP
An MCP server that exposes over 20 standard penetration testing utilities, such as Nmap, SQLMap, and OWASP ZAP, as callable tools for AI agents. It enables natural language control over complex security workflows for automated and interactive penetra
What is pentestMCP?
pentestMCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that exposes over 20 standard penetration testing utilities, such as nmap, sqlmap, and owasp zap, as callable tools for ai agents. it enables natural language control over complex security ...
An MCP server that exposes over 20 standard penetration testing utilities, such as Nmap, SQLMap, and OWASP ZAP, as callable tools for AI agents. It enables natural language control over complex security workflows for automated and interactive penetra
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP server that exposes over 20 standard penetration test
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx pentestmcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use pentestMCP
pentestMCP is a Docker-based MCP server that exposes over 20 standard penetration testing tools as callable functions for AI agents, covering reconnaissance (Nmap, Subfinder, theHarvester, WHOIS), web analysis (Gobuster, Arjun, OWASP ZAP), vulnerability scanning (Nuclei), exploitation (SQLMap, Searchsploit), and Active Directory attacks (Kerberoasting, DCSync, credential coercion). Security professionals can use it to conduct comprehensive penetration tests through natural language, letting the AI select appropriate tools and interpret results. It is intended strictly for authorized testing of systems you own or have explicit written permission to test.
Prerequisites
- Docker installed and running (the server is distributed as a Docker image)
- An MCP client such as Claude Desktop or VS Code with GitHub Copilot
- Explicit written authorization to test any target systems — unauthorized use is illegal
- Optional: SecLists wordlists cloned locally for Gobuster and related tools
Pull the pentestMCP Docker image
Pull the pre-built Docker image from Docker Hub. This includes all penetration testing tools pre-installed.
docker pull ramgameer/pentest-mcp:latestClone SecLists wordlists (optional but recommended)
Clone the SecLists repository for use with Gobuster directory and parameter brute-forcing. Mount it into the container when running.
git clone https://github.com/danielmiessler/SecLists.git seclistsAdd the server to your MCP client config
Configure Claude Desktop to run the pentestMCP Docker container as an MCP server using stdio transport.
Restart your MCP client
Restart Claude Desktop or VS Code to load the new pentestMCP server configuration. The Docker container will start automatically when the MCP client connects.
Run your first authorized scan
Ask your AI assistant to perform a scan on a target you have explicit authorization to test, such as your own lab environment or a CTF machine.
pentestMCP Examples
Client configuration
Add this to claude_desktop_config.json to run pentestMCP via Docker. Adjust volume mounts if you want to include SecLists.
{
"mcpServers": {
"pentestMCP": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ramgameer/pentest-mcp:latest"
]
}
}
}Prompts to try
Use natural language to direct penetration testing activities through your AI assistant. Only test systems you are authorized to test.
- "Perform an Nmap service and version scan on 192.168.1.10"
- "Run Subfinder to enumerate subdomains of example.com"
- "Use Gobuster to brute-force directories on http://192.168.1.10 using the common wordlist"
- "Run SQLMap against http://testsite.local/login.php to check for SQL injection"
- "Perform a Nuclei vulnerability scan on http://192.168.1.10 using the CVE templates"
- "Run theHarvester to collect emails and hostnames for example.com"Troubleshooting pentestMCP
Docker container exits immediately with no output
Run the container manually with 'docker run --rm -it ramgameer/pentest-mcp:latest /bin/bash' to inspect the environment and check for startup errors. Ensure Docker Desktop is running and has sufficient memory allocated.
Tools like Gobuster or Nuclei fail because wordlists or templates are missing
Mount local directories into the container using Docker volume flags. For SecLists, add '-v /path/to/seclists:/seclists' to the docker run args in your MCP config. Nuclei templates can be updated inside the container with 'nuclei -update-templates'.
Scan results are not returned or the AI reports a timeout
Long-running scans (large Nmap ranges, deep Gobuster runs) may exceed MCP response timeouts. Break scans into smaller target ranges, reduce thread counts, or use faster scan modes (e.g., Nmap -T4 with limited port ranges) to keep responses within the timeout window.
Frequently Asked Questions about pentestMCP
What is pentestMCP?
pentestMCP is a Model Context Protocol (MCP) server that mcp server that exposes over 20 standard penetration testing utilities, such as nmap, sqlmap, and owasp zap, as callable tools for ai agents. it enables natural language control over complex security workflows for automated and interactive penetra It connects AI assistants to external tools and data sources through a standardized interface.
How do I install pentestMCP?
Follow the installation instructions on the pentestMCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with pentestMCP?
pentestMCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is pentestMCP free to use?
Yes, pentestMCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
pentestMCP Alternatives — Similar Security Servers
Looking for alternatives to pentestMCP? 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 pentestMCP 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 pentestMCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.