Mcp ExploitationTier 1medium
MCP Exploitation: Tool Discovery
Attacks targeting Model Context Protocol integrations
Model Context Protocol (MCP) enables agents to interact with external tools and services. Each MCP connection is a potential attack surface that must be secured.
Attack Details
- Attack ID
- APWN-MCP-001
- HMA Check
- MCP-001
- Delivery Methods
- html-comment
- CWE
- CWE-200
- OASB Control
- 7.1
- Severity
- medium
Remediation
If your AI agent is vulnerable to this attack, scan and fix with:
npx hackmyagent secure --verbose
This page tests MCP-001. Look for that check ID in the scan output.
The vulnerable agent may not be the only one on the machine. The shadow AI audit inventories the AI tools, MCP servers and governance gaps across it, running or installed, one row per agent project, worst first:
npx hackmyagent detect