MCP MeasureMCP Measure

索引已觀測

Ban Bulkheads — Reputation Firebreaks for Agent Fleets

Partition an agent fleet into reputation compartments with automatic firebreaks.

我該用這個嗎

品質與安全性

B
說明品質
71%
結構描述完整度
74%
命名品質
89%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

發現項目（6）

  • LOWTool 'assign_agent' description lacks action verb在 assign_agent 中
  • LOWTool 'add_job' description lacks action verb在 add_job 中
  • LOWTool 'freeze_compartment' description lacks action verb在 freeze_compartment 中
  • LOWTool 'readmit' description lacks action verb在 readmit 中
  • LOWTool 'status_query' description lacks action verb在 status_query 中
  • LOWTool 'receipts' description lacks action verb在 receipts 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~473Token（工具定義）
~292 B典型回應大小
極小的注意力影響（128k 上下文的 0.37%）

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": {
    "ban-bulkheads-reputation-firebreaks": {
      "url": "https://textforagents.com/products/ban-bulkheads-reputation-firebreaks/mcp"
    }
  }
}

遠端端點

https://textforagents.com/products/ban-bulkheads-reputation-firebreaks/mcpstreamable-http

它能做什麼

工具清單

工具（9）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟡create_compartment(task_class)

Create a reputation compartment {task_class} (plan slot required)

輸入結構描述

{
  "type": "object",
  "properties": {
    "task_class": {
      "type": "string"
    }
  },
  "required": [
    "task_class"
  ]
}
⚪assign_agent(agent, compartment)

Assign an agent to a compartment {agent, compartment}

輸入結構描述

{
  "type": "object",
  "properties": {
    "agent": {
      "type": "string"
    },
    "compartment": {
      "type": "string"
    }
  },
  "required": [
    "agent",
    "compartment"
  ]
}
⚪record_outcome(compartment, outcome)

Record an outcome {compartment, outcome, job_id?, job_clean?}

輸入結構描述

{
  "type": "object",
  "properties": {
    "compartment": {
      "type": "string"
    },
    "outcome": {
      "type": "string"
    }
  },
  "required": [
    "compartment",
    "outcome"
  ]
}
🟡add_job(compartment, job_id)

Register an in-flight job {compartment, job_id, clean}

輸入結構描述

{
  "type": "object",
  "properties": {
    "compartment": {
      "type": "string"
    },
    "job_id": {
      "type": "string"
    }
  },
  "required": [
    "compartment",
    "job_id"
  ]
}
⚪penalty_signal(kind)

Intake an account-level penalty signal {kind}; attribution comes from baselines only

輸入結構描述

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string"
    }
  },
  "required": [
    "kind"
  ]
}
⚪freeze_compartment(compartment)

Freeze a compartment {compartment}

輸入結構描述

{
  "type": "object",
  "properties": {
    "compartment": {
      "type": "string"
    }
  },
  "required": [
    "compartment"
  ]
}
⚪readmit(compartment, probes)

Re-admission probes {compartment, probes}

輸入結構描述

{
  "type": "object",
  "properties": {
    "compartment": {
      "type": "string"
    },
    "probes": {
      "type": "array"
    }
  },
  "required": [
    "compartment",
    "probes"
  ]
}
🟢status_query(agent)

Compartment status for an agent {agent} — $0.01 x402 or included on an active plan (same billing as HTTP)

輸入結構描述

{
  "type": "object",
  "properties": {
    "agent": {
      "type": "string"
    }
  },
  "required": [
    "agent"
  ]
}
⚪receipts

Incident receipt chain + validity

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9 個工具