SeekinWeb — AI visibility
Does AI recommend a business? Who it names instead, which sources it uses, plus AI readability.
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": {
"ai-visibility": {
"url": "https://seekinweb.com/api/mcp"
}
}
}远程端点
https://seekinweb.com/api/mcpstreamable-http它能做什么
工具清单
工具（3）
🟢check_ai_recommendations(url, lang)
Checks whether an AI assistant with live web search recommends a business when a customer asks for what it offers, without naming it. Returns how many answers named the business, which brands were named instead, which websites the assistant relied on (the sources to be present on), and what the assistant says about the business. Runs in the background on first use (about a minute): if it reports that the test is running, call it again shortly. Free, no account.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Domain or URL of the site, e.g. \"example.com\" or \"https://example.com\". Use your own site or one you are authorized to review."
},
"lang": {
"type": "string",
"enum": [
"en",
"es"
],
"description": "Output language: \"en\" (default) or \"es\"."
}
},
"required": [
"url"
]
}🟢scan_website(url, lang)
Scans a website and returns its AI Visibility Score (0-100): whether AI crawlers and agents can find, read and cite it. Eight weighted signals (content readable without JavaScript, AI crawler access in robots.txt, structured data, semantic structure, metadata, performance, llms.txt, sitemap), each with a concrete fix when it fails. Free, no account.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Domain or URL of the site, e.g. \"example.com\" or \"https://example.com\". Use your own site or one you are authorized to review."
},
"lang": {
"type": "string",
"enum": [
"en",
"es"
],
"description": "Output language: \"en\" (default) or \"es\"."
}
},
"required": [
"url"
]
}🟢generate_llms_txt(url, lang)
Drafts an llms.txt file (llmstxt.org convention) for the root of a domain: a structured summary of the site for language models and agents, derived from the page's real content. Returns the file text. Note: llms.txt is an emerging convention with unproven impact.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Domain or URL of the site, e.g. \"example.com\" or \"https://example.com\". Use your own site or one you are authorized to review."
},
"lang": {
"type": "string",
"enum": [
"en",
"es"
],
"description": "Output language: \"en\" (default) or \"es\"."
}
},
"required": [
"url"
]
}社区
证据