phantom-mcp
Generates vulnerability reports formatted for Bugcrowd, suitable for bug bounty submissions.
Generates Elastic KQL queries from security findings for threat hunting and detection.
Generates vulnerability reports formatted for HackerOne, suitable for bug bounty submissions.
Allows using locally hosted Ollama models as the provider for PHANTOM tools, enabling offline or custom AI-powered analysis.
Allows using OpenAI's language models as the provider for PHANTOM tools, enabling AI-powered analysis and natural language processing.
Generates Splunk SPL queries from security findings for threat hunting and detection.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@phantom-mcpScan example.com for vulnerabilities"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
phantom-mcp
MCP Server for PHANTOM — exposes all PHANTOM capabilities as MCP tools for Claude Desktop, Cursor, and any MCP client.
Tools available
Tool | Description |
| Quick recon + vuln scan |
| Passive subdomain discovery only |
| Full red team pipeline (authorised use only) |
| Natural language → autonomous execution |
| Bug bounty / OSCP-style (no blind exploits) |
| Analyse a log file for IOCs and attacks |
| AI-powered hardening checklist |
| Incident response playbook from findings |
| Splunk SPL / Elastic KQL from findings |
| Generate a fake persona + disposable email |
| Check disposable email inbox |
| Wait for OTP in email |
| Poll for SMS OTP |
| Generate HackerOne / Bugcrowd / generic report |
| List all sessions |
| Get session findings (with severity filter) |
| Full session summary |
| General-purpose AI chat (any topic) |
| Ask AI to analyze your findings |
Related MCP server: GhostMap v2
Install
# 1. Install PHANTOM first
git clone https://github.com/grsanudeep42-cmd/phantom
cd phantom && pip install -e .
# 2. Install phantom-mcp (bundled in phantom/phantom-mcp)
pip install mcp # only extra dependencyConnect to Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or%APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"phantom": {
"command": "python",
"args": ["-m", "phantom_mcp.server.main"],
"cwd": "/absolute/path/to/phantom",
"env": {
"PYTHONPATH": "/absolute/path/to/phantom",
"ANTHROPIC_API_KEY": "sk-ant-..."
}
}
}
}Then restart Claude Desktop. You'll see all PHANTOM tools available.
LLM Provider
Every tool accepts optional provider and model arguments:
phantom_chat(message="explain XSS", provider="ollama", model="llama3.1")
phantom_scan(target="example.com", provider="openai", model="gpt-4o")Supported: anthropic, openai, ollama, openrouter, custom
Example usage in Claude Desktop
Use phantom_scan to scan example.com
Use phantom_grey to test example.com for bug bounty vulnerabilities
Use phantom_sessions_list to show my recent scans
Use phantom_findings with session_id="abc123" and severity="critical"
Use phantom_report with session_id="abc123" and format="hackerone"
Use phantom_chat to explain the CVE-2024-1234 vulnerabilityLicense
MIT © Anudeep | Part of the PHANTOM project
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Hyperion — MCP tool marketplace for AI agents: web, OSINT, security, research via one key.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceAn 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 penetration testing.105-
- FlicenseNot gradedqualityCmaintenanceExposes AI-augmented network reconnaissance and evasion capabilities as callable FastMCP tools, enabling natural language orchestration of host discovery, service fingerprinting, CVE mapping, and attack chain synthesis.1-
- FlicenseNot gradedqualityBmaintenanceExposes a hardened Docker container with Kali Linux security tools (nmap, sqlmap, dig, whois, etc.) as MCP tools, enabling network reconnaissance, web analysis, and vulnerability scanning through natural language commands.-
- AlicenseAqualityBmaintenanceExposes the Maester security test framework for Microsoft 365/Entra/Defender as MCP tools, enabling AI agents to run tests, audit AI agents and MCP servers, and investigate security posture.9MIT