Agent Receipts

Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
95%
命名质量
93%
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

~565token 数(工具定义)
~1.3 KB典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.44%)

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": {
    "agent-receipts": {
      "url": "https://agent-receipts.dropwatchhq.com/mcp"
    }
  }
}

远程端点

https://agent-receipts.dropwatchhq.com/mcpstreamable-http

它能做什么

工具清单

工具(3)

🟢 只读🟡 写入🔴 删除⚪ 未知
⚪issue_receipt(action, agent_id, inputs, outputs, inputs_hash, ...)

Mint a verifiable provenance receipt for an autonomous-agent action. Returns a signed (ed25519), content-hashed (SHA-256), server-timestamped receipt that is hash-chained to this agent's prior receipts (tamper-evident audit trail). Pass the raw inputs/outputs (we hash them — raw data is never stored) OR pre-computed sha256 hashes. Use for compliance, audit trails, and dispute resolution of agentic actions. PAID: $0.01 USDC/call via x402.

输入模式

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "description": "What the agent did, e.g. 'sent_payment' or 'approved_refund' or 'tool_call:search'."
    },
    "agent_id": {
      "type": "string",
      "description": "Stable identifier for the acting agent (chains group by this)."
    },
    "inputs": {
      "description": "Raw inputs to the action (any JSON). Hashed to a commitment; raw data not stored."
    },
    "outputs": {
      "description": "Raw outputs/result of the action (any JSON). Hashed to a commitment; raw data not stored."
    },
    "inputs_hash": {
      "type": "string",
      "description": "Alternatively, a pre-computed sha256 hex (or 'sha256:<hex>') of inputs."
    },
    "outputs_hash": {
      "type": "string",
      "description": "Alternatively, a pre-computed sha256 hex (or 'sha256:<hex>') of outputs."
    },
    "metadata": {
      "type": "object",
      "description": "Optional small key/value context (model, version, request id, etc.)."
    }
  },
  "required": [
    "action"
  ]
}
⚪verify_receipt(id, receipt)

Verify a receipt by id (or by passing the full receipt object). Recomputes the content hash, confirms the id commits to the body, and checks the ed25519 signature. Returns the verification checks plus the provenance record (action, agent, input/output hashes, timestamp, chain position). FREE.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Receipt id, e.g. 'rcpt_...'."
    },
    "receipt": {
      "type": "object",
      "description": "Alternatively, the full receipt object to verify offline-style."
    }
  }
}
🟢list_receipts(agent_id, limit)

List the receipt hash-chain for an agent_id, newest first (id, action, timestamp, sequence, hashes, verifyUrl). Use to audit everything a given agent has attested. FREE.

输入模式

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "The agent whose receipts to list."
    },
    "limit": {
      "type": "number",
      "description": "Max receipts (default 25, max 100)."
    }
  },
  "required": [
    "agent_id"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本3 个工具
已验证未记录版本3 个工具
已验证未记录版本3 个工具