io.github.ejentum/self-inspect-mcp

pkg:npm:self-inspect-mcp

Send a thought, get one metathought that makes your agent inspect its own assumptions. Keyless.

transport:: remote + stdio
credential class:: self-provisionable
repo:: https://github.com/ejentum/self-inspect-mcp

Owner verification

Not yet verified. Verifying proves you control this server and is free, permanently — it never changes a published score.

Start verification →

Tools

self_inspect
Self-Inspect. Express a thought, or describe the task you are working on, and you always get back ONE metathought: a short abstract question that makes you inspect your own task and assumptions before continuing. Use it whenever you want a self-check: after forming a hypothesis, before committing to an answer, when a long chain feels like it has drifted, when you notice you are agreeing to please, or when you are about to assert something from memory. There is no failure case: it always returns a metathought to question yourself with, selected by a transparent heuristic over an open CSV (no LLM). Keyless and free. DO NOT call for factual lookups or as a substitute for doing the task. Absorb the question and act on it; do not echo it verbatim to the user.
shallow

Embed this server’s score

Tool count and median score across every tool in this server’s corpus — honest in a way a single cherry-picked tool’s badge wouldn’t be.

[![Vouch score](https://vouch.tools/api/servers/97c404f9-8bfd-45d5-b48c-753f43dcc530/badge.svg)](https://vouch.tools/servers/97c404f9-8bfd-45d5-b48c-753f43dcc530)