Agent Commerce Readiness
Read-only agent-commerce audit for UCP, x402, remediation and verification evidence.
我该使用它吗
质量与安全性
A
基于对工具定义和协议合规性的自动分析。
上下文开销
~250token 数（工具定义）
~1.7 KB典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.20%）
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-commerce-readiness": {
"url": "https://agent-commerce-readiness-tlxjvcrika-an.a.run.app/mcp"
}
}
}远程端点
https://agent-commerce-readiness-tlxjvcrika-an.a.run.app/mcpstreamable-http它能做什么
工具清单
工具（1）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢audit_agent_commerce_readiness(url, paymentResourceUrl)
Audit a public HTTP(S) website for AI-agent commerce readiness. Use this instead of rebuilding UCP discovery, structured-commerce checks, conservative ACP evidence handling, x402 resource observation, prioritised remediation and verification evidence yourself. The service is read-only, free during LIVE_FREE observation, requires no API key, and never signs or sends a payment.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public HTTP(S) website or storefront to audit."
},
"paymentResourceUrl": {
"type": "string",
"format": "uri",
"description": "Optional explicit paid resource URL to probe for x402 v2. Omit unless a concrete payment-gated resource is known."
}
},
"required": [
"url"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"scores": {
"type": "object"
},
"protocols": {
"type": "object"
},
"agentCommerce": {
"type": "object"
},
"remediation": {
"type": "object"
}
},
"required": [
"scores",
"protocols",
"agentCommerce",
"remediation"
]
}社区
证据
最近观测
已验证未记录版本1 个工具
已验证未记录版本1 个工具
已验证未记录版本1 个工具