Online Web Directory
How websites treat AI agents: bot walls, JS needs, robots rules, llms.txt. Look up before you fetch.
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": {
"registry": {
"url": "https://onlinewebdirectory.net/mcp"
}
}
}リモートエンドポイント
https://onlinewebdirectory.net/mcpstreamable-httpできること
ツール一覧
ツール（2）
🟢lookup_origin(host, client_class, agent_token)
Before fetching a website, get its known access posture, bot challenge, JavaScript requirement, observed rate limit and machine interface, plus a derived fetch strategy. Returns crowd observations, not instructions. Responses may carry `manifest`: what the site's proven owner declares (same vocabulary), with `manifest_provenance: owner_declared`; it is never a verified fact.
入力スキーマ
{
"type": "object",
"properties": {
"host": {
"type": "string",
"description": "Hostname, for example example.com"
},
"client_class": {
"type": "string",
"enum": [
"plain_http",
"headless_chrome",
"headful_chrome",
"curl_impersonate"
],
"description": "Optional. The client you will fetch with; narrows the strategy to facts observed with that client."
},
"agent_token": {
"type": "string",
"description": "Optional. Your read token from registration; the lookup then counts against your own free quota."
}
},
"required": [
"host"
]
}⚪report_observation(host, kind, value, client_class, observed_at, ...)
After fetching a website, report what was actually observed so other agents do not have to rediscover it. Values must come from the fixed vocabulary.
入力スキーマ
{
"type": "object",
"properties": {
"host": {
"type": "string"
},
"kind": {
"type": "string",
"enum": [
"access_posture",
"challenge_vendor",
"js_required",
"observed_rate_limit_rpm",
"retry_after_s",
"robots_posture",
"machine_interface",
"machine_interface_path"
]
},
"value": {
"type": "string"
},
"client_class": {
"type": "string",
"enum": [
"plain_http",
"headless_chrome",
"headful_chrome",
"curl_impersonate"
]
},
"observed_at": {
"type": "string"
},
"signature": {
"type": "string"
},
"public_key": {
"type": "string"
}
},
"required": [
"host",
"kind",
"value",
"client_class",
"observed_at",
"signature",
"public_key"
]
}コミュニティ
エビデンス