Wake site readiness
How an AI agent sees a public website: robots, llms.txt, sitemap, agent card, scored fixes. Host in.
我該用這個嗎
品質與安全性
B
發現項目(1)
- LOW在 wake_about 中
根據工具定義與協定合規性的自動化分析。
上下文成本
~201Token(工具定義)
~305 B典型回應大小
極小的注意力影響(128k 上下文的 0.16%)
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": {
"wake-site-readiness": {
"url": "https://agent-observatory-desk-production.up.railway.app/api/wake/v1/public/mcp"
}
}
}遠端端點
https://agent-observatory-desk-production.up.railway.app/api/wake/v1/public/mcpstreamable-http它能做什麼
工具清單
工具(2)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢wake_check_site(host)
Probe a public hostname the way an AI agent sees it (homepage, robots.txt, llms.txt, sitemap, agent card) and return scores out of 100 with concrete recommendations and publish-ready llms.txt / robots files. Input is a hostname only; the probe keeps structural signals, never page bodies. No account needed.
輸入結構描述
{
"type": "object",
"properties": {
"host": {
"type": "string",
"description": "Public hostname, e.g. docs.example.com"
}
},
"additionalProperties": false
}🟢wake_about
One paragraph on Wake (agent experience observability + agent engine optimisation for a website), with links to docs, API, MCP and signup.
輸入結構描述
{
"type": "object",
"properties": {},
"additionalProperties": false
}社群
證據
近期觀測
已驗證未記錄版本2 個工具