What it does
The server offers three checks on AI agent output: an inline grounding check, detection of swallowed exceptions (errors that are caught and not reported), and review of agent transcripts. Its publisher describes the purpose as verifying agent claims against reality.
It falls under the development category and is listed as an MCP server, so it is relevant to developers who run AI agents and want to review whether their reported results match what occurred.
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
io.github.temurkhan13/openclaw-output-vetter-mcp
Verify AI agent claims vs reality: inline grounding-check + swallowed-exception + transcript review.
v1.3.0As shown on registry.modelcontextprotocol.io when we last read it