runvouch
Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.
我該用這個嗎
品質與安全性
發現項目（2）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains suspicious base64-like encoded string在 runvouch_status 中
根據工具定義與協定合規性的自動化分析。
上下文成本
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": {
"runvouch": {
"url": "https://api.runvouch.com/mcp"
}
}
}遠端端點
https://api.runvouch.com/mcpstreamable-http它能做什麼
工具清單
工具（7）
🟢runvouch_status
Health of all watched agents: state (ok/alert/failed/unproven/running/waiting), last run, 24h cost, open alerts.
輸入結構描述
{
"type": "object",
"properties": {}
}🟢runvouch_alerts
Open (un-acknowledged) alerts: MISSED, FAILED, NO_EVIDENCE, BUDGET_RUN, BUDGET_DAY, RETRY_STORM, DRIFT, STALLED.
輸入結構描述
{
"type": "object",
"properties": {}
}⚪runvouch_ack(alert_id)
Acknowledge an alert by id.
輸入結構描述
{
"type": "object",
"properties": {
"alert_id": {
"type": "integer"
}
},
"required": [
"alert_id"
]
}🟢runvouch_runs(agent, limit)
Recent runs of one agent.
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"type": "object",
"properties": {
"run_id": {
"type": "string"
}
},
"required": [
"run_id"
]
}社群
證據