manthanghasadiya/mcpsec
An AI-driven dynamic protocol fuzzer for the Model Context Protocol (MCP). Prove runtime exploitability by discovering state violations, transport crashes, and application-layer logic flaws (SSRF, LFI) before your AI agents do.
Combines runtime protocol fuzzing with 149 static Semgrep rules to test live MCP servers over stdio/HTTP transports, generating 800+ malformed payloads across 22 fuzzing strategies (type confusion, protocol violations, injection attacks). Includes AI-powered mutation, SQL injection fingerprinting, tool chain analysis, and a rogue server for testing client-side MCP implementations, integrated with SARIF output for CI/CD pipelines.
Available on PyPI.
Stars
3
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 05, 2026
Monthly downloads
655
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/manthanghasadiya/mcpsec"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
panther-labs/mcp-panther
Write detections, investigate alerts, and query logs from your favorite AI agents
duriantaco/skylos
High-precision Python SAST & Dead Code Remover. Finds unused functions, secrets, and security...
Wh0am123/MCP-Kali-Server
MCP configuration to connect AI agent to a Linux machine.
0x4m4/hexstrike-ai
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot,...
DMontgomery40/pentest-mcp
NOT for educational purposes: An MCP server for professional penetration testers including...