Testing MCP Server Security

Testing Model Context Protocol (MCP) servers and the clients that consume them for tool poisoning, prompt injection via tool descriptions/outputs, over-permissioned and local-credential-stealing tools, config/trust bypasses, and unauthenticated RCE during authorized penetration tests of AI agent infrastructure.

xalgord Updated 1.3k repo stars
Xalgorix — AI Autonomous Penetration Testing Platform

File contents

xalgord/xalgorix commit 6f951409b7

Frequently asked questions

npx get-skill add xalgord/testing-mcp-server-security