Skip to content

GLOSSARY, read 12 Nov 2026

Tool poisoning, defined with a sourced example

All glossary termsSee the full index

What is MCP tool poisoning?

Tool poisoning is hiding instructions in an MCP tool's description or metadata. The model reads them and may act on them, while the user usually sees only a short summary. Review tool descriptions, not only tool names, when you vet a server.

Example from a real source

Example

Invariant Labs described a Tool Poisoning Attack as malicious instructions embedded in MCP tool descriptions that are invisible to users but visible to AI models.

Where to read more

Sources

  1. invariantlabs.ai, read 12 Nov 2026

Last reviewed 12 Nov 2026.