agentglass
Scan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~155Token(工具定義)
~918 B典型回應大小
極小的注意力影響(128k 上下文的 0.12%)
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": {
"agentglass": {
"url": "https://agentglass.net/mcp"
}
}
}遠端端點
https://agentglass.net/mcpstreamable-http它能做什麼
工具清單
工具(1)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪scan_job_page(url, timeoutMs)
Scan a public URL, typically a job posting or application page, for hidden text, HTML comments, metadata and script content that try to instruct an AI agent (prompt injection). Returns a risk level (clean, notice, suspicious, high), a short verdict and the evidence, so the agent can decide whether to continue or pause for human review.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public URL to inspect, such as a job application page."
},
"timeoutMs": {
"type": "number",
"minimum": 5000,
"maximum": 45000,
"description": "Optional scan timeout in milliseconds."
}
},
"required": [
"url"
],
"additionalProperties": false
}社群
證據
近期觀測
已驗證未記錄版本1 個工具
已驗證未記錄版本1 個工具
已驗證未記錄版本1 個工具