Your MCP config might be one unpinned version away from a supply chain attack.

If you're running MCP servers in Claude Desktop, Claude Code, Cursor, or VS Code, that config file is now part of your attack surface, and most developers never check it against anything.

The pattern behind recent incidents

The MCPoison and ContextCrush incidents both followed the same playbook:

A config gets approved once, looking completely benign

It's silently updated to a malicious version later

Or a tampered server feeds attacker-controlled instructions directly into the AI agent's context

Because MCP servers have direct access to your AI agent's working memory and can invoke tools on your behalf, a compromised server can exfiltrate credentials or execute commands with no visible indication anything is wrong.

What MCPConfigCheck does

Paste your mcp.json or claude_desktop_config.json and it instantly checks for:

Known incident matches : cross-referenced against a maintained catalog of disclosed MCP supply chain…