What it does
The publisher describes agent-check as process monitoring for AI agents. It works in three steps: a run is started, evidence is submitted for each task, and the run is completed.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
agent-check
Process monitoring for AI agents: start runs, submit per-task evidence, complete runs.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it