# io.github.ejentum/self-inspect-mcp (npm · self-inspect-mcp)

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

- Trust score: 63/100 (medium)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `api.ejentum.com`: 65/100, [markdown](https://verifymcp.io/servers/ejentum-self-inspect-mcp/self-inspect-mcp.md), [page](https://verifymcp.io/servers/ejentum-self-inspect-mcp/self-inspect-mcp)
- npm · `self-inspect-mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/ejentum-self-inspect-mcp/self-inspect-mcp-2.md), [page](https://verifymcp.io/servers/ejentum-self-inspect-mcp/self-inspect-mcp-2)

## Channel facts

- Registry: `npm`
- Package: `self-inspect-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 52 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 42/100
  - AI-judged instruction clarity (poor).
  - Context-footprint check failed: tool/resource definitions use about 231 tokens (~231/item across 1 items; 1 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add ejentum-self-inspect-mcp -- npx -y self-inspect-mcp
```

### Codex

```bash
codex mcp add ejentum-self-inspect-mcp -- npx -y self-inspect-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ejentum-self-inspect-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "self-inspect-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ejentum-self-inspect-mcp --command npx --arg -y --arg self-inspect-mcp
```

### Hermes

```yaml
mcp_servers:
  ejentum-self-inspect-mcp:
    command: "npx"
    args: ["-y", "self-inspect-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "ejentum-self-inspect-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "self-inspect-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 63, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 59, +39)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → poor
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified
- [functional] Licence: MIT

### 2026-08-01 (score 20, −7)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 27, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 45)

First indexed and scored.

## MCP tools (1)

### `self_inspect` (~231 tokens)

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.

Input parameters:

- `thought` (string, required): A free-text thought or a description of the task you are working on. Express what you are doing or thinking; the more concrete, the sharper the returned question. Example: 'I'm about to assert the de…

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ejentum-self-inspect-mcp/self-inspect-mcp-2#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 59
- 2026-08-01: 20
- 2026-07-31: 27
- 2026-07-30: 45
- 2026-07-28: 45
- 2026-07-27: 45

## Links

- npm package: https://www.npmjs.com/package/self-inspect-mcp
- Socket report: https://socket.dev/npm/package/self-inspect-mcp
- Repository: https://github.com/ejentum/self-inspect-mcp
- Changelog RSS feed: https://verifymcp.io/servers/ejentum-self-inspect-mcp/self-inspect-mcp-2/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ejentum-self-inspect-mcp/self-inspect-mcp-2/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ejentum-self-inspect-mcp/self-inspect-mcp-2