self-inspect-mcp
Send a thought, get one metathought that makes your agent inspect its own assumptions. Keyless.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"self-inspect-mcp": {
"command": "npx",
"args": [
"self-inspect-mcp"
]
}
}
}可运行的软件包
0.1.1stdio远程端点
https://api.ejentum.com/self-inspect-mcpstreamable-http它能做什么
工具清单
工具（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.
输入模式
{
"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#"
}社区
证据