Siteiz
Check which AI crawlers a site allows and see pages the way AI crawlers do. Free, read-only.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"siteiz": {
"url": "https://siteiz.com/mcp"
}
}
}リモートエンドポイント
https://siteiz.com/mcpstreamable-httpできること
ツール一覧
ツール（4）
🟢check_ai_crawlers(url)
Reads a website's robots.txt and reports, for 11 AI crawlers (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, PerplexityBot, Google-Extended, Applebot-Extended, Meta-ExternalAgent, CCBot, Bytespider), whether each may reach the given page. Separates AI search crawlers (decide if the site appears in ChatGPT, Claude and Perplexity answers) from training crawlers. Also reports llms.txt and declared sitemaps.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Website or page address, e.g. example.com or https://example.com/pricing"
}
},
"required": [
"url"
],
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": [
"string",
"null"
]
},
"robotsTxt": {
"type": "string",
"enum": [
"ok",
"missing",
"unreachable",
"invalid",
"pasted"
]
},
"httpStatus": {
"type": [
"integer",
"null"
]
},
"agents": {
"type": "array",
"items": {
"type": "object",
"properties": {
"token": {
"type": "string"
},
"verdict": {
"type": "string",
"enum": [
"allowed",
"default",
"blocked"
]
},
"operator": {
"type": "string"
},
"role": {
"type": "string",
"enum": [
"search",
"user",
"training",
"control"
]
}
},
"required": [
"token",
"verdict",
"operator",
"role"
]
}
},
"llmsTxt": {
"type": [
"boolean",
"null"
]
},
"sitemaps": {
"type": "array",
"items": {
"type": "string"
}
},
"contentSignals": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"url",
"robotsTxt",
"agents"
]
}🟢view_page_as_ai_crawler(url)
Fetches one page the way most AI crawlers do (plain HTTP, no JavaScript) and reports what they actually receive: title, meta description, canonical, H1, heading count, structured data types, visible word count, token reading cost, and a text preview. Use it to check whether content is visible to AI without JavaScript.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Website or page address, e.g. example.com or https://example.com/pricing"
}
},
"required": [
"url"
],
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"finalUrl": {
"type": "string"
},
"status": {
"type": "integer"
},
"bytes": {
"type": "integer"
},
"title": {
"type": [
"string",
"null"
]
},
"metaDescription": {
"type": [
"string",
"null"
]
},
"canonical": {
"type": [
"string",
"null"
]
},
"h1": {
"type": "array",
"items": {
"type": "string"
}
},
"headingCount": {
"type": "integer"
},
"structuredData": {
"type": "array",
"items": {
"type": "string"
}
},
"words": {
"type": "integer"
},
"htmlTokens": {
"type": "integer"
},
"textTokens": {
"type": "integer"
},
"fullScan": {
"type": "string"
}
},
"required": [
"finalUrl",
"status",
"words",
"fullScan"
]
}🟢explain_ai_crawler(name)
Explains what an AI crawler user agent does (operator, purpose, and what blocking it in robots.txt changes). Pass a name such as GPTBot or OAI-SearchBot, or omit it to list all crawlers Siteiz tracks.
入力スキーマ
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Crawler user agent, e.g. GPTBot. Omit to list all."
}
},
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"crawlers": {
"type": "array",
"items": {
"type": "object",
"properties": {
"token": {
"type": "string"
},
"operator": {
"type": "string"
},
"product": {
"type": "string"
},
"role": {
"type": "string"
},
"roleLabel": {
"type": "string"
},
"does": {
"type": "string"
}
},
"required": [
"token",
"operator",
"role",
"does"
]
}
}
},
"required": [
"crawlers"
]
}🟢get_ai_visibility_report(company)
Returns a published, dated Siteiz AI visibility report for a well-known company's homepage (score, grade, pillar scores, top issues). Omit the company to list all published reports.
入力スキーマ
{
"type": "object",
"properties": {
"company": {
"type": "string",
"description": "Company name, e.g. Notion. Omit to list all reports."
}
},
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"reports": {
"type": "array",
"items": {
"type": "object",
"properties": {
"company": {
"type": "string"
},
"score": {
"type": "integer"
},
"grade": {
"type": "string"
},
"scannedAt": {
"type": "string"
},
"url": {
"type": "string"
}
}
}
},
"company": {
"type": "string"
},
"url": {
"type": "string"
},
"scannedAt": {
"type": "string"
},
"score": {
"type": "integer"
},
"grade": {
"type": "string"
},
"pillars": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"label": {
"type": "string"
},
"score": {
"type": "integer"
},
"notAssessed": {
"type": "boolean"
}
}
}
},
"report": {
"type": "string"
}
},
"description": "Either `reports` (a list, when no company matched) or the single report fields."
}コミュニティ
エビデンス