petra402
Public web page to markdown, paid per call with x402. First 10 calls free, no signup.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
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": {
"petra402": {
"url": "https://petra402.com/mcp?src=mcp-registry"
}
}
}远程端点
https://petra402.com/mcp?src=mcp-registrystreamable-http它能做什么
工具清单
工具（1）
🟢scrape(url, fresh, max_chars, links, max_age_seconds)
Fetch a public web page and return its main content as markdown. Charged per successful call with x402: 0.005 USDC on Base Sepolia (testnet). A failed scrape is never charged, and a cache hit inside 24 h is free. Payment happens at the HTTP transport layer: an unpaid call answers 402 with the payment requirements; sign and repeat the identical JSON-RPC call with the payment header. This server speaks x402 v2 (PAYMENT-SIGNATURE / PAYMENT-RESPONSE), not v1 (X-PAYMENT). A v1 client will loop on 402 without ever settling. Refusals that are policy and never charged: government, military and any health-related domain; private or internal addresses; paths disallowed by robots.txt; sites protected by an anti-bot vendor (never bypassed).
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "absolute http(s) URL of a public page"
},
"fresh": {
"type": "boolean",
"description": "bypass the 24 h cache (a cache hit is free; fresh is always charged)"
},
"max_chars": {
"type": "number",
"description": "truncate the markdown; the answer reports truncated and chars_total"
},
"links": {
"type": "boolean",
"description": "keep link targets in the markdown"
},
"max_age_seconds": {
"type": "number",
"description": "accept a cached copy only if it is younger than this"
}
},
"required": [
"url"
],
"additionalProperties": false
}社区
证据