self-inspect-mcp
Send a thought, get one metathought that makes your agent inspect its own assumptions. Keyless.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"self-inspect-mcp": {
"command": "npx",
"args": [
"self-inspect-mcp"
]
}
}
}実行可能なパッケージ
0.1.1stdioリモートエンドポイント
https://api.ejentum.com/self-inspect-mcpstreamable-httpできること
ツール一覧
ツール（1）
🟢self_inspect(thought)
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.
入力スキーマ
{
"type": "object",
"properties": {
"thought": {
"type": "string",
"minLength": 1,
"description": "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."
}
},
"required": [
"thought"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}コミュニティ
エビデンス