polygraphso

AI agents plug into third-party tools and load skills that can hijack them or leak your data. We run those tools through an adversarial test, scan those skills for the same tricks, and publish a letter grade — free to read, public, evidence attached.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

模型生成摘要（rules/v1 · 2026-09-27 16:41）：AI agents plug into third-party tools and load skills that can hijack them or leak your data
这是模型对公开材料的总结，不是官方声明，请以原链内容为准。

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://polygraphso--ruben-sousa-dinis.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "polygraphso": {
      "url": "https://polygraphso--ruben-sousa-dinis.run.tools"
    }
  }
}

能力清单

工具	说明
check_server	Read a server's published behavioral grade (A–F) from polygraph.so in under a second — no execution. The pre-flight check before recommending or installing an MCP server. On a miss it returns not_available (unevaluated — neither safe nor unsafe) with next steps.
list_servers	Every MCP server that carries a published polygraph grade, sorted A-first.
request_grade	Add an ungraded MCP server to polygraph.so's public grading queue (free, best-effort). Read the result later with check_server. Only real, plausibly-MCP targets are accepted.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。