MCP MeasureMCP Measure

索引已觀測

Agent Handoff

Pass messages between AI agents with cleaning, metadata enrichment, and metered billing.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
65%
命名品質
90%
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

~209Token（工具定義）
~566 B典型回應大小
極小的注意力影響（128k 上下文的 0.16%）

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": {
    "agent-handoff": {
      "url": "https://agent-handoff-production-573c.up.railway.app/mcp"
    }
  }
}

遠端端點

https://agent-handoff-production-573c.up.railway.app/mcpstreamable-http

它能做什麼

工具清單

工具（2）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪handoff(message, next_agent)

Hand a message off to another agent. Cleans and normalizes the payload, stamps it with handoff metadata (id, timestamp, estimated tokens, target agent), and records the handoff. Use this when passing work or context from one agent to the next in a multi-agent pipeline. This is a metered, billable operation.

輸入結構描述

{
  "type": "object",
  "properties": {
    "message": {
      "description": "The payload to hand off. Accepts a plain string or a JSON object. Max 256 KB.",
      "type": [
        "string",
        "object",
        "array",
        "number",
        "boolean"
      ]
    },
    "next_agent": {
      "type": "string",
      "description": "Name/identifier of the agent receiving this handoff.",
      "maxLength": 128
    }
  },
  "required": [
    "message",
    "next_agent"
  ]
}
🟢get_usage_stats

Return this account's total handoff count and the most recent handoffs. Read-only and not billed.

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2 個工具
已驗證未記錄版本2 個工具
已驗證未記錄版本2 個工具