Agent Ready
Score any website out of 100 for how well AI agents can find, understand and use it.
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": {
"agent-ready": {
"url": "https://agentready.sneeze.it/mcp"
}
}
}リモートエンドポイント
https://agentready.sneeze.it/mcpstreamable-httpできること
ツール一覧
ツール（4）
🟢scan_website(url, fresh)
Score any public website out of 100 for how well AI agents can use it: reach it, understand it, act on it (book, quote, buy), complete the task, act for a signed-in customer, trust its facts, and find the right location. Returns the score, a score per area, the most important finding in each area, and a link to the full report with every finding and the ordered fix plan. Takes 5 to 20 seconds.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The website to scan, for example acme.com or https://www.acme.com/"
},
"fresh": {
"type": "boolean",
"description": "Rescan even if the site was scanned in the last 30 minutes. Use after the owner changed something."
}
},
"required": [
"url"
]
}🟢get_report(report)
Fetch a report that was already run, by its report link or id, without scanning again.
入力スキーマ
{
"type": "object",
"properties": {
"report": {
"type": "string",
"description": "A report URL (https://agentready.sneeze.it/report/...) or report id."
}
},
"required": [
"report"
]
}🟢explain_check(check)
Explain what one check measures, what it is worth and where to read how to fix it. Pass the check name as it appears in a report, for example "WebMCP tools an agent can call".
入力スキーマ
{
"type": "object",
"properties": {
"check": {
"type": "string",
"description": "The check name, or a few words from it."
}
},
"required": [
"check"
]
}🟢get_scoring_method
The scored areas, their weights and every check, so a score can be explained.
入力スキーマ
{
"type": "object",
"properties": {}
}コミュニティ
エビデンス