MCP MeasureMCP Measure

索引已观测

Refusal Desk — pre-execution task-brief tribunal

The Refusal Desk builds the *no* — a pre-execution tribunal that screens an incoming task brief

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
68%
命名质量
90%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~486token 数（工具定义）
~1.0 KB典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.38%）

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": {
    "refusal-desk-task-brief-tribunal": {
      "url": "https://textforagents.com/products/refusal-desk-task-brief-tribunal/mcp"
    }
  }
}

远程端点

https://textforagents.com/products/refusal-desk-task-brief-tribunal/mcpstreamable-http

它能做什么

工具清单

工具（4）

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢check_brief(brief, standing_rules)

Screen a task brief before execution {brief, standing_rules?} — $0.01 / trial grant / Fleet quota (same billing as HTTP)

输入模式

{
  "type": "object",
  "properties": {
    "brief": {
      "type": "object",
      "properties": {
        "requester": {
          "type": "string"
        },
        "principal_id": {
          "type": "string"
        },
        "title": {
          "type": "string"
        },
        "goal": {
          "type": "string"
        },
        "deliverable": {
          "type": "string"
        },
        "acceptance": {
          "type": "string"
        },
        "constraints": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "budget_usd": {
          "type": "number"
        },
        "tools": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "deadline_epoch": {
          "type": "number"
        },
        "estimated_execution_usd": {
          "type": "number"
        }
      },
      "required": [
        "principal_id",
        "goal"
      ]
    },
    "standing_rules": {
      "type": "array",
      "items": {
        "type": "object"
      }
    }
  },
  "required": [
    "brief"
  ]
}
⚪settle_outcome(verdict_id, outcome, failure_class, result, cost_usd)

Settle a verdict {verdict_id, outcome, failure_class?, result?, cost_usd?} — idempotent; a forecast miss prices $0.05 against the per-principal per-period cap

输入模式

{
  "type": "object",
  "properties": {
    "verdict_id": {
      "type": "string"
    },
    "outcome": {
      "type": "string",
      "enum": [
        "success",
        "failure"
      ]
    },
    "failure_class": {
      "type": "string"
    },
    "result": {
      "type": "string"
    },
    "cost_usd": {
      "type": "number"
    }
  },
  "required": [
    "verdict_id",
    "outcome"
  ]
}
🟢duplicate_lookup(brief)

Cross-requester semantic duplicate search {brief} — +$0.02 x402

输入模式

{
  "type": "object",
  "properties": {
    "brief": {
      "type": "object",
      "properties": {
        "requester": {
          "type": "string"
        },
        "principal_id": {
          "type": "string"
        },
        "title": {
          "type": "string"
        },
        "goal": {
          "type": "string"
        },
        "deliverable": {
          "type": "string"
        },
        "acceptance": {
          "type": "string"
        },
        "constraints": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "budget_usd": {
          "type": "number"
        },
        "tools": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "deadline_epoch": {
          "type": "number"
        },
        "estimated_execution_usd": {
          "type": "number"
        }
      },
      "required": [
        "principal_id",
        "goal"
      ]
    }
  },
  "required": [
    "brief"
  ]
}
⚪calibration_report

Own per-class calibration + miss accounting

输入模式

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

社区

评价此服务器

证据

最近观测

已验证未记录版本4 个工具