A growing collection of MCP servers bringing offensive security tools to AI assistants. Nmap, Ghidra, Nuclei, SQLMap, Hashcat and more.
Offensive Security MCP Servers
Production-ready, Dockerized MCP (Model Context Protocol) servers for offensive security tools. Enable AI assistants like Claude to perform security assessments, vulnerability scanning, and binary analysis.
Features
- 38 MCP Servers covering reconnaissance, web security, binary analysis, blockchain security, cloud security, code security, secrets detection, threat intelligence, OSINT, Active Directory, fuzzing, and more
- 300+ Security Tools accessible via natural language through Claude or other MCP clients
- Production Hardened - Non-root containers, minimal images, Trivy-scanned
- Docker Compose orchestration for multi-tool workflows
- CI/CD Ready with GitHub Actions for automated builds and security scanning
Quick Start
# Clone the repository
git clone https://github.com/FuzzingLabs/mcp-security-hub
cd mcp-security-hub
Build all MCP servers
docker-compose build
Start specific servers
docker-compose up nmap-mcp nuclei-mcp -d
Verify health
docker-compose ps
Configure Claude Desktop / Claude Code
Important: You must build the images first with docker-compose build before using them.
Copy the example config to your Claude Desktop configuration:
macOS: ~/Library/Application Support/Claude/claudedesktopconfig.json
Windows: %APPDATA%\Claude\claudedesktopconfig.json
{
"mcpServers": {
"nmap": {
"command": "docker",
"args": ["run", "-i", "--rm", "--cap-add=NET_RAW", "nmap-mcp:latest"]
},
"nuclei": {
"command": "docker",
"args": ["run", "-i", "--rm", "nuclei-mcp:latest"]
},
"gitleaks": {
"command": "docker",
"args": ["run", "-i", "--rm", "-v", "/path/to/repos:/app/target:ro", "gitleaks-mcp:latest"]
},
"radare2": {
"command": "docker",
"args": ["run", "-i", "--rm", "-v", "/path/to/binaries:/samples:ro", "radare2-mcp:latest"]
}
}
}
For project-level config, copy .mcp.json to your project root. See examples/ for full configuration templates with all MCPs and volume mount patterns.
Available MCP Servers
Reconnaissance (8 servers)
| Server | Tools | Description | |--------|-------|-------------| | nmap-mcp | 8 | Port scanning, service detection, OS fingerprinting, NSE scripts | | shodan-mcp | - | Wrapper for official Shodan MCP | | pd-tools-mcp | - | Wrapper for ProjectDiscovery tools (subfinder, httpx, katana) | | whatweb-mcp | 5 | Web technology fingerprinting and CMS detection | | masscan-mcp | 6 | High-speed port scanning for large networks | | zoomeye-mcp | - | Wrapper for ZoomEye MCP - Cyberspace search engine | | networksdb-mcp | 4 | IP/ASN/DNS lookups via NetworksDB | | externalattacker-mcp | 6 | Attack surface mapping with ExternalAttacker |
Web Security (6 servers)
| Server | Tools | Description | |--------|-------|-------------| | nuclei-mcp | 7 | Template-based vulnerability scanning with 8000+ templates | | sqlmap-mcp | 8 | SQL injection detection and exploitation | | nikto-mcp | - | Wrapper for Nikto MCP web server scanner | | ffuf-mcp | 9 | Web fuzzing for directories, files, parameters, and virtual hosts | | waybackurls-mcp | 3 | Fetch historical URLs from Wayback Machine for reconnaissance | | burp-mcp | - | Wrapper for official Burp Suite MCP |
Binary Analysis (6 servers)
| Server | Tools | Description | |--------|-------|-------------| | radare2-mcp | 32 | Wrapper for official radare2-mcp - disassembly, decompilation | | binwalk-mcp | 6 | Firmware analysis, signature scanning, extraction | | yara-mcp | 7 | Pattern matching for malware classification | | capa-mcp | 5 | Capability detection in executables | | ghidra-mcp | - | Wrapper for pyghidra-mcp - Headless AI-powered reverse engineering | | ida-mcp | - | Wrapper for ida-pro-mcp - IDA Pro integration |
Blockchain Security (3 servers)
| Server | Tools | Description | |--------|-------|-------------| | daml-viewer-mcp | 1 | DAML access-control table generation and run tracking | | medusa-mcp | 4 | High-performance smart contract fuzzer for Solidity | | solazy-mcp | 8 | Solana sBPF static analysis and reverse engineering |
Cloud Security (3 servers)
| Server | Tools | Description | |--------|-------|-------------| | trivy-mcp | 7 | Container, filesystem, and IaC vulnerability scanning | | prowler-mcp | 6 | AWS/Azure/GCP security auditing and compliance | | roadrecon-mcp | 6 | Azure AD enumeration via RoadRecon |
Secrets Detection (1 server)
| Server | Tools | Description | |--------|-------|-------------| | gitleaks-mcp | 5 | Find secrets and credentials in git repos and files |
Exploitation (1 server)
| Server | Tools | Description | |--------|-------|-------------| | searchsploit-mcp | 5 | Exploit-DB search and retrieval |
Fuzzing (2 servers)
| Server | Tools | Description | |--------|-------|-------------| | boofuzz-mcp | 4 | Network protocol fuzzing using Boofuzz | | dharma-mcp | 2 | Grammar-based test case generation |
OSINT (2 servers)
| Server | Tools | Description | |--------|-------|-------------| | maigret-mcp | - | Wrapper for mcp-maigret - Username OSINT across 2500+ sites | | dnstwist-mcp | - | Wrapper for mcp-dnstwist - Typosquatting/phishing detection |
Threat Intelligence (2 servers)
| Server | Tools | Description | |--------|-------|-------------| | virustotal-mcp | - | Wrapper for mcp-virustotal - Malware analysis and threat intel | | otx-mcp | - | Wrapper for OTX MCP - AlienVault Open Threat Exchange |
Active Directory (1 server)
| Server | Tools | Description | |--------|-------|-------------| | bloodhound-mcp | 75+ | Wrapper for BloodHound-MCP-AI - AD attack path analysis |
Password Cracking (1 server)
| Server | Tools | Description | |--------|-------|-------------| | hashcat-mcp | - | Wrapper for hashcat-mcp - Natural language hash cracking |
Code Security (1 server)
| Server | Tools | Description | |--------|-------|-------------| | semgrep-mcp | 7 | Wrapper for Semgrep MCP - Static code analysis with 5000+ rules |
Meta (1 server)
| Server | Tools | Description | |--------|-------|-------------| | mcp-scan | - | Wrapper for mcp-scan - Scan MCP servers for vulnerabilities |
Usage Examples
Network Reconnaissance
You: "Scan 192.168.1.0/24 for web servers and identify technologies"
Claude: I'll perform a network scan and technology fingerprinting. [Uses nmap-mcp to scan ports 80,443,8080] [Uses whatweb-mcp to fingerprint discovered hosts]
Found 12 web servers:
- 192.168.1.10: Apache 2.4.52, WordPress 6.4
- 192.168.1.15: nginx 1.24, React application
...
Vulnerability Assessment
You: "Check example.com for common vulnerabilities"
Claude: I'll run a vulnerability scan using nuclei templates. [Uses nuclei-mcp with cves, exposures, and misconfigurations templates]
Found 3 issues:
- HIGH: CVE-2024-1234 - Outdated jQuery version
- MEDIUM: Exposed .git directory
- INFO: Missing security headers
Binary Analysis
You: "Analyze this firmware image for security issues"
Claude: I'll extract and analyze the firmware. [Uses binwalk-mcp to extract filesystem] [Uses yara-mcp to scan for malware patterns] [Uses capa-mcp to identify capabilities]
Analysis complete:
- Extracted 847 files from SquashFS filesystem
- Found hardcoded credentials in /etc/shadow
- Identified network backdoor capability
Security Hardening
All containers implement defense-in-depth:
| Control | Implementation | |---------|----------------| | Non-root execution | Runs as mcpuser (UID 1000) | | Minimal images | Alpine/Debian slim base images | | Dropped capabilities | capdrop: ALL, selective capadd | | No privilege escalation | security_opt: no-new-privileges:true | | Read-only mounts | Sample directories mounted read-only | | Resource limits | CPU and memory constraints | | Health checks | Built-in container health monitoring | | Vulnerability scanning | Trivy scans in CI/CD pipeline |
Project Structure
mcp-security-hub/
โโโ reconnaissance/
โ โโโ nmap-mcp/ # Port scanning
โ โโโ shodan-mcp/ # Internet device search (wrapper)
โ โโโ pd-tools-mcp/ # ProjectDiscovery tools (wrapper)
โ โโโ whatweb-mcp/ # Web fingerprinting
โ โโโ masscan-mcp/ # High-speed scanning
โ โโโ zoomeye-mcp/ # Cyberspace search (wrapper)
โ โโโ networksdb-mcp/ # IP/ASN/DNS lookups
โ โโโ externalattacker-mcp/ # Attack surface mapping
โโโ web-security/
โ โโโ nuclei-mcp/ # Vulnerability scanning
โ โโโ sqlmap-mcp/ # SQL injection
โ โโโ nikto-mcp/ # Web server scanning (wrapper)
โ โโโ ffuf-mcp/ # Web fuzzing
โ โโโ burp-mcp/ # Burp Suite (wrapper)
โโโ binary-analysis/
โ โโโ radare2-mcp/ # Reverse engineering (wrapper)
โ โโโ binwalk-mcp/ # Firmware analysis
โ โโโ yara-mcp/ # Malware detection
โ โโโ capa-mcp/ # Capability detection
โ โโโ ghidra-mcp/ # Ghidra RE - pyghidra-mcp (headless)
โ โโโ ida-mcp/ # IDA Pro (wrapper)
โโโ blockchain/
โ โโโ daml-viewer-mcp/ # DAML access-control analysis
โ โโโ medusa-mcp/ # Smart contract fuzzing
โ โโโ solazy-mcp/ # Solana analysis
โโโ cloud-security/
โ โโโ trivy-mcp/ # Container scanning (wrapper)
โ โโโ prowler-mcp/ # Cloud auditing
โ โโโ roadrecon-mcp/ # Azure AD enumeration
โโโ code-security/
โ โโโ semgrep-mcp/ # Static code analysis (wrapper)
โโโ secrets/
โ โโโ gitleaks-mcp/ # Secrets detection
โโโ exploitation/
โ โโโ searchsploit-mcp/ # Exploit database
โโโ fuzzing/
โ โโโ boofuzz-mcp/ # Network protocol fuzzing using Boofuzz
โ โโโ dharma-mcp/ # Grammar-based test case generation
โโโ osint/
โ โโโ maigret-mcp/ # Username OSINT (wrapper)
โ โโโ dnstwist-mcp/ # Typosquatting detection (wrapper)
โโโ threat-intel/
โ โโโ virustotal-mcp/ # Malware analysis (wrapper)
โ โโโ otx-mcp/ # AlienVault OTX (wrapper)
โโโ active-directory/
โ โโโ bloodhound-mcp/ # AD attack paths (wrapper)
โโโ password-cracking/
โ โโโ hashcat-mcp/ # Hash cracking (wrapper)
โโโ meta/
โ โโโ mcp-scan/ # MCP security scanning
โโโ scripts/
โ โโโ setup.sh # Quick setup
โ โโโ healthcheck.sh # Health verification
โโโ tests/
โ โโโ testmcpservers.py # Unit tests
โโโ docker-compose.yml # Orchestration
โโโ .github/workflows/ # CI/CD
Testing
# Run unit tests
pytest tests/ -v
Build and test all Docker images
./scripts/test_builds.sh
Test MCP protocol (after building)
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | \
docker run -i --rm nmap-mcp:latest
Legal & Compliance
These tools are for authorized security testing only.
Before using:
- Obtain written authorization from the target owner
- Define scope - targets, timeline, allowed activities
- Maintain audit logs of all operations
- Follow responsible disclosure for any findings
Contributing
Contributions welcome! To add a new MCP server:
- Use
Dockerfile.templateas your starting point - Follow security hardening practices (non-root, minimal image)
- Include health checks and comprehensive README
- Ensure Trivy scan passes (no HIGH/CRITICAL vulnerabilities)
- Add tests to
tests/testmcpservers.py
Acknowledgments
- Model Context Protocol - Protocol specification
- awesome-mcp-security - MCP security catalog
- Upstream tool maintainers: nmap, nuclei, radare2, sqlmap, and all others
License
MIT License - See LICENSE
Maintained by FuzzingLabs
Making AI-powered security testing accessible