Nyxstrike
AI Powered penetration testing Platform for offensive security research
What is Nyxstrike?
Nyxstrike is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai powered penetration testing platform for offensive security research
AI Powered penetration testing Platform for offensive security research
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- AI Powered penetration testing Platform for offensive securi
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx nyxstrikeConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Nyxstrike
NyxStrike (formerly Hexstrike AI Community Edition) is an AI-powered offensive security orchestration engine that connects LLM agents to over 185 real penetration testing tools and executes full attack chains — from network reconnaissance through exploitation to report generation. It exposes all tools via an MCP interface, so any MCP-compatible client (Claude Desktop, Cursor, VS Code Copilot) can drive recon, enumeration, web exploitation, OSINT, password attacks, and cloud security assessments through natural-language prompts. It is designed for authorized penetration testing, bug bounty programs, CTF competitions, and red team exercises.
Prerequisites
- Python 3.13 or later installed
- Docker and Docker Compose installed (recommended for the full tool stack)
- A Linux environment or security-focused VM — Kali Linux is the recommended base
- An MCP-compatible client such as Claude Desktop, Cursor, or OpenCode
- Written authorization for any target system you test (legal requirement)
Clone the repository
Download NyxStrike to your testing machine or dedicated security VM.
git clone https://github.com/CommonHuman-Lab/nyxstrike.git
cd nyxstrikeRun the setup and start the server
The nyxstrike.sh script handles environment setup, dependency installation, and starting the MCP server and dashboard. Use the -ai flag to also spin up a local AI model.
chmod +x nyxstrike.sh
./nyxstrike.sh -a # Setup + start server
# OR with local AI model:
./nyxstrike.sh -a -ai # includes ~8.4 GB model
./nyxstrike.sh -a -ai-small # includes ~2.5 GB modelOr start with Docker Compose
For a fully containerized setup, use Docker Compose to build and run the entire stack.
docker compose up --build -dVerify the dashboard is running
Open a browser and navigate to the dashboard. All tool outputs and live command logs appear here.
# Open in browser:
http://localhost:8888Configure your MCP client
Add the NyxStrike MCP server to your AI client by pointing it at the Python MCP bridge script.
{
"mcpServers": {
"nyxstrike": {
"type": "local",
"command": [
"/path/to/nyxstrike/nyxstrike-env/bin/python3",
"/path/to/nyxstrike/nyxstrike_mcp.py",
"--server", "http://127.0.0.1:8888",
"--profile", "full"
]
}
}
}Nyxstrike Examples
Client configuration
JSON config for connecting Claude Desktop to a locally running NyxStrike server using the Python MCP bridge.
{
"mcpServers": {
"nyxstrike": {
"command": "/path/to/nyxstrike/nyxstrike-env/bin/python3",
"args": [
"/path/to/nyxstrike/nyxstrike_mcp.py",
"--server", "http://127.0.0.1:8888",
"--profile", "full"
]
}
}
}Prompts to try
Example prompts for authorized penetration testing and security research tasks.
- "Run a port scan on 192.168.1.10 and list open services"
- "Perform a web application scan on https://testsite.example.com"
- "Search for public information about the domain example.com using OSINT tools"
- "Check for common misconfigurations in this target's HTTP headers"
- "Generate a penetration test report summarizing findings from this session"Troubleshooting Nyxstrike
Some scan tools (nmap, masscan) fail with permission errors
Raw socket operations require elevated privileges. Run the server as root or with sudo inside your dedicated testing VM. Never run as root on a shared or production machine.
MCP client cannot connect to the NyxStrike server
Check that the server is running by visiting http://localhost:8888 in a browser. Verify the path to nyxstrike_mcp.py and the Python interpreter inside nyxstrike-env are correct absolute paths.
Docker Compose build fails with dependency errors
Ensure Docker and Docker Compose are up to date. Try 'docker compose down --volumes' to clear stale state, then 'docker compose up --build -d' again.
Frequently Asked Questions about Nyxstrike
What is Nyxstrike?
Nyxstrike is a Model Context Protocol (MCP) server that ai powered penetration testing platform for offensive security research It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Nyxstrike?
Follow the installation instructions on the Nyxstrike GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Nyxstrike?
Nyxstrike works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Nyxstrike free to use?
Yes, Nyxstrike is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Nyxstrike Alternatives — Similar Security Servers
Looking for alternatives to Nyxstrike? 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 Nyxstrike 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 Nyxstrike?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.