AI & Machine Learning
runvouch.com
Tracks and reports the operational status of AI agents, including their run history, alerts, and acknowledgement.
ENDPOINT 1
https://api.runvouch.com/mcp
MCP server metadata
- Name
- runvouch
- Version
- 0.3.0
Known tools 6
runvouch_statusHealth of all watched agents: state (ok/alert/failed/unproven/running/waiting), last run, 24h cost, open alerts.
Inferred read-onlyrunvouch_alertsOpen (un-acknowledged) alerts: MISSED, FAILED, NO_EVIDENCE, BUDGET_RUN, BUDGET_DAY, RETRY_STORM, DRIFT, STALLED.
Inferred read-onlyrunvouch_run_endReport that a run ended, with status and evidence dict (name -> bool or {type:'url',url}).
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.runvouch]
url = "https://api.runvouch.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"runvouch": {
"type": "http",
"url": "https://api.runvouch.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: runvouch
Remote MCP URL: https://api.runvouch.com/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"runvouch": {
"url": "https://api.runvouch.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"runvouch": {
"type": "http",
"url": "https://api.runvouch.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "runvouch",
"transport": "streamable-http",
"url": "https://api.runvouch.com/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.