CyberStrikeAI
CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and compr
What is CyberStrikeAI?
CyberStrikeAI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to cyberstrikeai is an ai-native security testing platform built in go. it integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills...
CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and compr
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- CyberStrikeAI is an AI-native security testing platform buil
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx cyberstrikeaiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use CyberStrikeAI
CyberStrikeAI is an AI-native security testing platform built in Go that integrates 100+ security tools (nmap, sqlmap, nuclei, metasploit, trivy, masscan, nikto, and more) behind an intelligent orchestration engine accessible through natural language via MCP and a REST API. It supports role-based testing with predefined security personas, a skills system for specialized attack-chain testing, lifecycle management for engagements, and a built-in lightweight C2 (Command & Control) framework for authorized assessments with encrypted implants and session management. Security professionals and red teams use it to automate the full penetration testing lifecycle — from reconnaissance through exploitation and reporting — through conversational AI commands rather than manual tool invocation.
Prerequisites
- Go 1.21+ and Python 3.10+ installed on the testing machine
- The security tools you want to use installed and accessible on PATH (nmap, nuclei, sqlmap, etc.)
- An OpenAI-compatible API key (OpenAI, DeepSeek, or any compatible provider)
- An MCP-compatible client such as Claude Desktop or Cursor for the MCP interface
- This platform is for authorized security testing only — only use on systems you own or have explicit written permission to test
Clone the repository
Clone CyberStrikeAI and enter the project directory. The platform is distributed as source and built locally.
git clone https://github.com/Ed1s0nZ/CyberStrikeAI.git
cd CyberStrikeAIRun the startup script
The `run.sh` script handles dependency installation, environment setup, and launches the HTTPS server. An auto-generated strong password is displayed in the terminal output on first run.
chmod +x run.sh
./run.shAccess the web interface and configure API credentials
Open the browser to https://127.0.0.1:8080 (accept the self-signed certificate warning), log in with the generated password, then go to Settings and enter your LLM provider API key, base URL, and model name.
# Settings fields to configure:
# api_key: sk-your-openai-or-compatible-key
# base_url: https://api.openai.com/v1
# model: gpt-4o (or deepseek-chat, etc.)Enable the MCP server
In config.yaml (or via the web UI settings), enable the MCP server. By default it runs on port 8081. Configure optional header-based authentication for the MCP endpoint.
# config.yaml snippet
mcp:
enabled: true
port: 8081
auth_header: X-MCP-Token
auth_header_value: your-secret-tokenConfigure your MCP client
Add CyberStrikeAI's MCP server to your Claude Desktop or other MCP client configuration, pointing at the local HTTP MCP endpoint.
{
"mcpServers": {
"cyberstrikeai": {
"command": "npx",
"args": ["cyberstrikeai"]
}
}
}Select a security role and run your first scan
In the UI, select a predefined security role (e.g., web pentester, network auditor) or create a custom role with specific tool restrictions. Then send a natural language command to begin testing.
CyberStrikeAI Examples
Client configuration
Claude Desktop configuration for CyberStrikeAI MCP server.
{
"mcpServers": {
"cyberstrikeai": {
"command": "npx",
"args": ["cyberstrikeai"]
}
}
}Prompts to try
Example prompts for AI-driven security testing through CyberStrikeAI (use only on authorized targets).
- "Scan open ports on 192.168.1.100 and identify running services"
- "Check if https://target.example.com/login?id=1 is vulnerable to SQL injection"
- "Enumerate subdomains for target.example.com then run nuclei against the discovered assets"
- "Run a container vulnerability scan on the nginx:1.21 image using trivy"
- "Generate an attack-chain graph for the findings from the last scan session"Troubleshooting CyberStrikeAI
run.sh fails with Go build errors
Ensure Go 1.21+ is installed and `go` is on your PATH. Run `go version` to check. If dependencies fail to download, check your internet connection or set GOPROXY to a mirror: `export GOPROXY=https://goproxy.io,direct`.
Security tools return 'command not found' errors during scans
CyberStrikeAI shells out to security tools that must be independently installed. Install the required tools (e.g., `apt install nmap sqlmap nuclei` on Debian/Ubuntu) and ensure they are on the PATH of the user running CyberStrikeAI.
MCP client cannot connect to the CyberStrikeAI MCP endpoint
Verify the MCP server is enabled in config.yaml (`mcp.enabled: true`) and the service is running on port 8081. If auth_header is configured, ensure your MCP client sends the correct header value in its requests.
Frequently Asked Questions about CyberStrikeAI
What is CyberStrikeAI?
CyberStrikeAI is a Model Context Protocol (MCP) server that cyberstrikeai is an ai-native security testing platform built in go. it integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and compr It connects AI assistants to external tools and data sources through a standardized interface.
How do I install CyberStrikeAI?
Follow the installation instructions on the CyberStrikeAI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with CyberStrikeAI?
CyberStrikeAI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is CyberStrikeAI free to use?
Yes, CyberStrikeAI is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
CyberStrikeAI Alternatives — Similar Security Servers
Looking for alternatives to CyberStrikeAI? 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 CyberStrikeAI 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 CyberStrikeAI?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.