Parallel World
Check which AI bots a site's robots.txt allows; read-only facts about Parallel World
我該用這個嗎
品質與安全性
發現項目（2）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domain在 check_ai_bot_access 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"parallel-world": {
"url": "https://pw.migurei.ai/mcp"
}
}
}遠端端點
https://pw.migurei.ai/mcpstreamable-http它能做什麼
工具清單
工具（2）
🟢get_site_info(topic)
Returns the facts published on this website, in Japanese: service overview, plans, prices and payment terms, how the scanner behaves, how to contact us, and the operating company. Each fact comes with the URL of the page that shows it. Read-only; it returns nothing that is not on the pages.
輸入結構描述
{
"type": "object",
"properties": {
"topic": {
"type": "string",
"enum": [
"overview",
"pricing",
"scanner",
"contact",
"company",
"all"
],
"description": "Which facts to return"
}
},
"required": [
"topic"
],
"additionalProperties": false
}🟢check_ai_bot_access(domain)
Reads the public robots.txt of a website (one request to https://<host>/robots.txt, nothing else on the site) and says, for each AI crawler and AI agent of the migurei bot registry (training crawlers such as GPTBot and ClaudeBot, search bots, fetchers that act for a user, and others), whether that bot is allowed or disallowed for the path "/", which robots.txt rule decided it, and whether the file exists. Each bot also carries observed_on_pw: the counts our own lab site pw.migurei.ai recorded for that bot (published on https://pw.migurei.ai/ja/research/ai-bot-first-visits; the same for every domain, not about the domain asked, not a prediction). Input is a domain or URL; only public domain names are accepted (no IP addresses, no ports, no private hosts). Read-only; the domain is not stored. robots.txt is a request to bots, not access control, and a User-Agent is only a claim.
輸入結構描述
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"maxLength": 300,
"description": "A public domain name or a URL, for example example.com or https://example.com/page. Only its host is used."
}
},
"required": [
"domain"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"domain": {
"type": "string"
},
"robots_url": {
"type": "string"
},
"robots_txt": {
"type": "object",
"properties": {
"state": {
"type": "string",
"enum": [
"found",
"not_found",
"unavailable"
]
},
"http_status": {
"type": [
"integer",
"null"
]
},
"error": {
"type": [
"string",
"null"
]
},
"redirects": {
"type": "integer"
},
"truncated": {
"type": "boolean"
},
"bytes": {
"type": "integer"
},
"possible_block": {
"type": "boolean"
}
},
"required": [
"state",
"http_status",
"error",
"redirects",
"truncated",
"bytes",
"possible_block"
]
},
"bots": {
"type": "array",
"items": {
"type": "object",
"properties": {
"bot": {
"type": "string"
},
"token": {
"type": "string"
},
"category": {
"type": "string",
"enum": [
"training",
"search_index",
"user_fetch",
"browser_agent",
"unknown"
]
},
"verdict": {
"type": "string",
"enum": [
"allowed",
"disallowed",
"unknown"
]
},
"basis": {
"type": "string",
"enum": [
"bot_group",
"wildcard_group",
"googlebot_group",
"no_group",
"no_robots_txt",
"robots_txt_unavailable"
]
},
"rule": {
"type": [
"string",
"null"
]
},
"path_rules": {
"type": "boolean"
},
"observed_on_pw": {
"type": "object",
"description": "What our lab saw this bot do on its own site pw.migurei.ai (counts published on the source page). Not about the domain asked, not a prediction. The same for every domain asked.",
"properties": {
"site": {
"type": "string"
},
"applies_to_queried_domain": {
"type": "boolean"
},
"observed": {
"type": "boolean"
},
"first_seen": {
"type": [
"string",
"null"
]
},
"last_seen": {
"type": [
"string",
"null"
]
},
"robots_txt_fetches": {
"type": [
"integer",
"null"
]
},
"pages_fetched": {
"type": [
"integer",
"null"
]
},
"sitemap_urls": {
"type": [
"integer",
"null"
]
},
"window": {
"type": "object",
"properties": {
"from": {
"type": "string"
},
"to": {
"type": "string"
}
},
"required": [
"from",
"to"
]
},
"as_of": {
"type": "string"
},
"source": {
"type": "string"
},
"code_sha": {
"type": "string"
},
"note_ja": {
"type": "string"
},
"note_en": {
"type": "string"
}
},
"required": [
"site",
"applies_to_queried_domain",
"observed",
"first_seen",
"last_seen",
"robots_txt_fetches",
"pages_fetched",
"sitemap_urls",
"window",
"as_of",
"source",
"code_sha",
"note_ja",
"note_en"
]
}
},
"required": [
"bot",
"token",
"category",
"verdict",
"basis",
"rule",
"path_rules"
]
}
},
"summary": {
"type": "object",
"properties": {
"allowed": {
"type": "integer"
},
"disallowed": {
"type": "integer"
},
"unknown": {
"type": "integer"
}
},
"required": [
"allowed",
"disallowed",
"unknown"
]
},
"registry_version": {
"type": "string"
},
"method": {
"type": "string"
},
"learn_more": {
"type": "string"
}
},
"required": [
"domain",
"robots_url",
"robots_txt",
"bots",
"summary",
"registry_version",
"method",
"learn_more"
]
}社群
證據