AI 101

Malicious MCP server

Also known as: bad MCP ยท MCP attack

Security

A malicious MCP server is a Model Context Protocol server that presents legitimate-looking tools but behaves maliciously โ€” exfiltrating, misdirecting, or poisoning.

  • Looks like a normal integration.
  • Exposes tools that leak data or mislead the model.
  • A supply-chain vector specific to the agent ecosystem.

The check: before wiring in an MCP server, audit what tools it exposes and what data they can reach. An MCP server is code you're giving agent-level trust to.