MCP MeasureMCP Measure

索引已觀測

Tool-Confusability Recovery Loop

Recovery loop for agent tool catalogs: measured confusion, ranked fixes, signed recovery receipts.

我該用這個嗎

品質與安全性

A
說明品質
97%
結構描述完整度
80%
命名品質
87%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~352Token（工具定義）
~332 B典型回應大小
極小的注意力影響（128k 上下文的 0.27%）

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案：

{
  "mcpServers": {
    "tool-confusability-regression-gate": {
      "url": "https://textforagents.com/products/tool-confusability-regression-gate/mcp"
    }
  }
}

遠端端點

https://textforagents.com/products/tool-confusability-regression-gate/mcpstreamable-http

它能做什麼

工具清單

工具（6）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪register_catalog(catalog, probes)

Register a tool catalog + probe suite; stores the green state. Free.

輸入結構描述

{
  "type": "object",
  "properties": {
    "catalog": {
      "type": "array"
    },
    "probes": {
      "type": "array"
    }
  },
  "required": [
    "catalog",
    "probes"
  ]
}
⚪start_loop(catalog_id, catalog, selector_class)

Start a recovery loop run against the current live catalog ($0.05 / plan / first run free).

輸入結構描述

{
  "type": "object",
  "properties": {
    "catalog_id": {
      "type": "string"
    },
    "catalog": {
      "type": "array"
    },
    "selector_class": {
      "type": "string"
    }
  },
  "required": [
    "catalog_id",
    "catalog"
  ]
}
⚪apply_fix(loop_id, item)

Serve the revised catalog for a chosen worklist item of an open loop run.

輸入結構描述

{
  "type": "object",
  "properties": {
    "loop_id": {
      "type": "string"
    },
    "item": {
      "type": "integer"
    }
  },
  "required": [
    "loop_id",
    "item"
  ]
}
⚪verify_recovery(loop_id)

Re-probe a loop run whose fix was served and return the signed recovery receipt.

輸入結構描述

{
  "type": "object",
  "properties": {
    "loop_id": {
      "type": "string"
    }
  },
  "required": [
    "loop_id"
  ]
}
🟡server_author_verdict(tool, stack)

Server-author pre-publish verdict: measure one submitted tool against the curated reference stacks; every verdict names its stack.

輸入結構描述

{
  "type": "object",
  "properties": {
    "tool": {
      "type": "object"
    },
    "stack": {
      "type": "string"
    }
  },
  "required": [
    "tool"
  ]
}
🟢loop_status(loop_id)

Fetch a loop run's status and receipt.

輸入結構描述

{
  "type": "object",
  "properties": {
    "loop_id": {
      "type": "string"
    }
  },
  "required": [
    "loop_id"
  ]
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本6 個工具