cyber-mcp-server
A production-style MCP server providing AI models with cybersecurity tools including port scanning, WHOIS, DNS, threat intelligence, CVE lookup, and more.
README
Cybersecurity MCP Server
A production-style MCP (Model Context Protocol) server that gives AI models a toolkit of real cybersecurity capabilities — port scanning, WHOIS, DNS, threat intelligence, CVE lookup, and more.
Claude / ChatGPT
│
Model Context Protocol
│
Cyber MCP Server
│
┌────┬────┬──────┬──────┬─────┬───────┬────────┐
Nmap DNS WHOIS VT ABUSE NVD Hash URL
Tools
| Tool | What it does | External API |
|---|---|---|
scan_host |
Nmap TCP scan on a single host | — |
scan_range |
Nmap sweep across a CIDR block | — |
whois_lookup |
Registrar, dates, nameservers | — |
dns_lookup |
A/AAAA/MX/NS/TXT/CNAME/SOA records | — |
check_ip_reputation |
Malicious flag, abuse score, ISP | VirusTotal, AbuseIPDB |
check_url_reputation |
Detection ratio, categories | VirusTotal |
analyze_hash |
MD5/SHA1/SHA256 file hash lookup | VirusTotal |
search_cve |
CVSS score, description, CPEs | NVD (NIST) |
check_password_strength |
zxcvbn score, entropy, crack time | — (fully local) |
scan_url |
SSL cert, redirect chain, risk score | — |
Quick start
1. Clone & install
git clone https://github.com/yourname/cyber-mcp-server.git
cd cyber-mcp-server
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
2. Configure
cp .env.example .env
# Edit .env — add your API keys
3. Run (stdio — for Claude Desktop)
python server.py
4. Run (SSE — for HTTP clients)
MCP_TRANSPORT=sse python server.py
# Server starts on http://0.0.0.0:8000
5. Docker
docker compose up --build
Claude Desktop integration
Add to claude_desktop_config.json:
{
"mcpServers": {
"cyber": {
"command": "python",
"args": ["/absolute/path/to/cyber-mcp-server/server.py"],
"env": {
"API_KEYS": "your-key",
"VIRUSTOTAL_API_KEY": "...",
"ABUSEIPDB_API_KEY": "...",
"NVD_API_KEY": "..."
}
}
}
}
Example prompts (in Claude)
Scan scanme.nmap.org and summarize the open services.
Is 185.220.101.1 a malicious IP?
Look up CVE-2024-3400 and explain the risk.
Check the password "Summer2024!" — is it strong?
Analyse the hash d41d8cd98f00b204e9800998ecf8427e.
Scan https://example.com for SSL and security header issues.
Do a full DNS lookup for google.com.
Project structure
cyber-mcp-server/
├── server.py # Entry point — registers all tools
├── config/
│ └── settings.py # Env-based configuration
├── tools/
│ ├── nmap_tool.py # Port scanner
│ ├── whois_tool.py # WHOIS lookup
│ ├── dns_tool.py # DNS records
│ ├── vt_tool.py # VirusTotal / AbuseIPDB
│ ├── hash_tool.py # File hash analysis
│ ├── cve_tool.py # NVD CVE lookup
│ ├── password_tool.py # Password strength (local)
│ └── url_tool.py # SSL + redirect + header scan
├── middleware/
│ ├── auth.py # API key + JWT auth
│ ├── rate_limit.py # Token-bucket rate limiter
│ └── audit.py # Structured JSON audit logs
├── utils/
│ └── helpers.py # Shared utilities
├── tests/
│ └── test_tools.py # Pytest unit tests
├── logs/ # Auto-created at runtime
├── .env.example # Environment variable template
├── .github/workflows/ci.yml # GitHub Actions CI/CD
├── Dockerfile
├── docker-compose.yml
├── pytest.ini
└── requirements.txt
API keys needed
| Service | Get key | Free tier |
|---|---|---|
| VirusTotal | https://virustotal.com | 4 req/min |
| AbuseIPDB | https://abuseipdb.com | 1000 req/day |
| NVD (NIST) | https://nvd.nist.gov/developers/request-an-api-key | 50 req/30s |
Testing
pytest tests/ -v --cov=. --cov-report=term-missing
Security notes
- Nmap scans should only target hosts you have permission to scan.
- Passwords evaluated by
check_password_strengthare never logged or sent externally. - All tool calls are written to
logs/audit.logas newline-delimited JSON. - Run the container as a non-root user (already configured in
Dockerfile). - Rotate
API_KEYSandJWT_SECRETbefore deploying to production.
Resume features checklist
- [x] MCP + FastMCP integration
- [x] 8 cybersecurity tools
- [x] API key authentication
- [x] JWT token support
- [x] Rate limiting (token bucket)
- [x] Structured audit logging
- [x] Docker + docker-compose
- [x] GitHub Actions CI/CD
- [x] Pytest unit tests with coverage
- [x] Async throughout (httpx, asyncio)
- [x] Secure non-root Docker image
- [x]
.env-based configuration "# cyber-mcp-server"
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.