runvouch
Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.
使うべきか
品質と安全性
検出事項(2)
- HIGH
- MEDIUMrunvouch_status 内
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": {
"runvouch": {
"url": "https://api.runvouch.com/mcp"
}
}
}リモートエンドポイント
https://api.runvouch.com/mcpstreamable-httpできること
ツール一覧
ツール(7)
🟢runvouch_status
Health of all watched agents: state (ok/alert/failed/unproven/running/waiting), last run, 24h cost, open alerts.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢runvouch_alerts
Open (un-acknowledged) alerts: MISSED, FAILED, NO_EVIDENCE, BUDGET_RUN, BUDGET_DAY, RETRY_STORM, DRIFT, STALLED.
入力スキーマ
{
"type": "object",
"properties": {}
}⚪runvouch_ack(alert_id)
Acknowledge an alert by id.
入力スキーマ
{
"type": "object",
"properties": {
"alert_id": {
"type": "integer"
}
},
"required": [
"alert_id"
]
}🟢runvouch_runs(agent, limit)
Recent runs of one agent.
入力スキーマ
{
"type": "object",
"properties": {
"agent": {
"type": "string"
},
"limit": {
"type": "integer",
"default": 20
}
},
"required": [
"agent"
]
}⚪runvouch_run_start(agent, source)
Report that a run of `agent` started. Returns run_id.
入力スキーマ
{
"type": "object",
"properties": {
"agent": {
"type": "string"
},
"source": {
"type": "string"
}
},
"required": [
"agent"
]
}⚪runvouch_run_end(run_id, status, cost, tokens, evidence)
Report that a run ended, with status and evidence dict (name -> bool or {type:'url',url}). Green run without evidence alerts.
入力スキーマ
{
"type": "object",
"properties": {
"run_id": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"ok",
"fail"
]
},
"cost": {
"type": "number"
},
"tokens": {
"type": "integer"
},
"evidence": {
"type": "object"
}
},
"required": [
"run_id"
]
}🟢runvouch_run_proof(run_id)
Tamper-evident proof of a finished run: hashed record, Merkle path, day root, chain hash and OpenTimestamps status. Verify offline with templates/verify_proof.py.
入力スキーマ
{
"type": "object",
"properties": {
"run_id": {
"type": "string"
}
},
"required": [
"run_id"
]
}コミュニティ
エビデンス