ai-visibility

AI-search-visibility tools: check crawler access, generate llms.txt, lint robots.txt, census data.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
97%
命名质量
95%
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

~350token 数(工具定义)
~572 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.27%)

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": {
    "ai-visibility": {
      "url": "https://ai-visibility.lastminutedealshq.com/mcp"
    }
  }
}

远程端点

https://ai-visibility.lastminutedealshq.com/mcpstreamable-http

它能做什么

工具清单

工具(4)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢check_site(url)

Check a site's AI search visibility: which AI crawlers (OAI-SearchBot, PerplexityBot, GPTBot, ClaudeBot and more) robots.txt allows, whether the homepage ships readable text without JavaScript, and whether an llms.txt exists.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "A site to check, e.g. example.com or https://example.com"
    }
  },
  "required": [
    "url"
  ]
}
⚪generate_llms_txt(url, credit)

Generate an llms.txt file from a site's real pages and sitemap.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "A site to generate an llms.txt for"
    },
    "credit": {
      "type": "boolean",
      "description": "Include a one-line attribution back to this tool. Default true."
    }
  },
  "required": [
    "url"
  ]
}
⚪validate_llms_txt(url)

Validate an existing llms.txt against the spec.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "A site whose /llms.txt should be fetched and validated"
    }
  },
  "required": [
    "url"
  ]
}
🟢lint_robots_txt(url, robots_txt)

Lint a robots.txt for AI-crawler-specific mistakes. Pass url to fetch it live, or robots_txt to lint pasted text directly.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "A site whose /robots.txt should be fetched and linted"
    },
    "robots_txt": {
      "type": "string",
      "description": "Raw robots.txt text to lint directly, instead of fetching url"
    }
  }
}

社区

评价此服务器

证据

最近观测

已验证未记录版本4 个工具
已验证未记录版本4 个工具
已验证未记录版本4 个工具