praetorian-inc/MCPHammer
MCP security testing framework for evaluating Model Context Protocol server vulnerabilities
This is a framework for security testers to evaluate Model Context Protocol (MCP) servers. It takes in various commands, including queries to Claude AI, and can inject custom text into responses or execute files. Security professionals can use this to probe vulnerabilities and test the robustness of MCP-based systems.
Use this if you are a security professional or penetration tester needing to assess the security posture of MCP server implementations.
Not ideal if you are looking for a general-purpose AI client or a production-ready system for securely interacting with AI models.
Stars
23
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/praetorian-inc/MCPHammer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Wh0am123/MCP-Kali-Server
MCP configuration to connect AI agent to a Linux machine.
DMontgomery40/pentest-mcp
NOT for educational purposes: An MCP server for professional penetration testers including...
BurtTheCoder/mcp-shodan
MCP server for Shodan — search internet-connected devices, IP reconnaissance, DNS lookups, and...
cyproxio/mcp-for-security
MCP for Security: A collection of Model Context Protocol servers for popular security tools like...
0x4m4/hexstrike-ai
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot,...