vouch
Check if a counterparty is safe to pay: trust/risk score for AI agents. Scam/phishing screen.
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": {
"vouch": {
"url": "https://vouch.futuronoti.workers.dev/mcp"
}
}
}リモートエンドポイント
https://vouch.futuronoti.workers.dev/mcpstreamable-httpできること
ツール一覧
ツール(2)
🟡vouch_score(target)
Check whether a counterparty is SAFE TO PAY before sending money. Given a URL or host, returns a 0-100 trust score and risk band (low/medium/high/critical), detecting scams, phishing, and known-malicious endpoints via threat feeds, domain risk heuristics, and a community reputation graph. Call this before paying any merchant, API, agent, or x402 resource. Free — for the full explainable reasons AND a signed, verifiable attestation (proof of the check for audit/disputes), call the paid POST /v1/check endpoint via x402.
入力スキーマ
{
"type": "object",
"properties": {
"target": {
"type": "string",
"description": "Counterparty URL or hostname."
}
},
"required": [
"target"
],
"additionalProperties": false
}⚪vouch_report(target, kind, reason)
Report a host as a scam/bad actor ('flag') or as trustworthy ('vouch'), improving Vouch's community reputation graph for everyone's future payment-trust checks. Free.
入力スキーマ
{
"type": "object",
"properties": {
"target": {
"type": "string"
},
"kind": {
"type": "string",
"enum": [
"flag",
"vouch"
]
},
"reason": {
"type": "string"
}
},
"required": [
"target",
"kind"
],
"additionalProperties": false
}コミュニティ
エビデンス