Blog
Keeping AI agents in bounds.
Notes for engineers who ship agents: what goes wrong when agents call tools, and how to check actions before they run.
No posts yet
In the meantime, the explainers cover the same ground in depth.
MCP Guard
Check your agent's next tool call before it runs.
A verdict (allow, ask or block) and nine calibrated scores in one call. It reduces risk; it does not replace your permissions, allowlists and backups. 1,000 free requests, then $0.20 per 1,000 checks.