MCP MeasureMCP Measure

索引已觀測

Sampling Quota Guard

Per-server MCP sampling allowance, scope clamp and pre-connect verdict.

我該用這個嗎

品質與安全性

B
說明品質
83%
結構描述完整度
65%
命名品質
80%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

發現項目（1）

  • LOWTool 'guard_ledger' description lacks action verb在 guard_ledger 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~246Token（工具定義）
~219 B典型回應大小
極小的注意力影響（128k 上下文的 0.19%）

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": {
    "sampling-quota-guard": {
      "url": "https://textforagents.com/products/sampling-quota-guard/mcp"
    }
  }
}

遠端端點

https://textforagents.com/products/sampling-quota-guard/mcpstreamable-http

它能做什麼

工具清單

工具（4）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪guard_meter(server, request)

Meter one sampling/createMessage request against your per-server ledger + fail-closed allowance + scope clamp. Billed per the pricing sheet (flat coverage, then $0.002 x402). Denied requests never consume allowance.

輸入結構描述

{
  "type": "object",
  "properties": {
    "server": {
      "type": "string"
    },
    "request": {
      "type": "object"
    }
  },
  "required": [
    "server",
    "request"
  ]
}
⚪guard_verdict(server)

Pre-connect verdict (ALLOW / CAUTION / DENY / INSUFFICIENT_DATA) for one server from your own measured profile. First 100 verdicts free one time per operator; then $0.005 x402; flat tier covers verdicts.

輸入結構描述

{
  "type": "object",
  "properties": {
    "server": {
      "type": "string"
    }
  },
  "required": [
    "server"
  ]
}
⚪guard_ledger(server)

Your per-server sampling ledger rows (your operator only).

輸入結構描述

{
  "type": "object",
  "properties": {
    "server": {
      "type": "string"
    }
  }
}
⚪guard_policy

Your allowance + tunable threshold policy.

輸入結構描述

{
  "type": "object",
  "properties": {}
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本4 個工具