agent-check is listed as active in the registry but did not answer our last check.
Process monitoring for AI agents: start runs, submit per-task evidence, complete runs.
agent-check does not always answer
Over the last week it answered 77.2% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 16 min ago.
claude mcp add agent-check --transport http https://agent-check.basenull.com/api/mcp/{token}{
"mcpServers": {
"agent-check": {
"url": "https://agent-check.basenull.com/api/mcp/{token}"
}
}
}[mcp_servers.agent-check]
url = "https://agent-check.basenull.com/api/mcp/{token}"{
"mcpServers": {
"agent-check": {
"url": "https://agent-check.basenull.com/api/mcp/{token}"
}
}
}{
"mcpServers": {
"agent-check": {
"url": "https://agent-check.basenull.com/api/mcp/{token}"
}
}
}Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agent-check.basenull.com/api/mcp/{token} | streamable-http | answering | 20 ms | 16 min ago |
Alternatives to agent-check
same job, measured the same wayFMCSA motor-carrier risk scores, monitoring, and carrier-selection evidence reports for AI agents.
Screenshots, PDFs, OG images, monitoring and evidence for AI agents. Glint Render by Moyu.
Process management and monitoring for AI agents with strict security boundaries
Site & competitor monitoring: snapshots, evidence-backed diffs, briefs, price checks, mentions.
Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.
MCP server for Docker — containers, health checks, Compose, logs, monitoring for AI agents
Your agent pings once per run; get a public up/late/down status page. Auto-creates checks. One call.
Checks agent traces for evidence-readiness: verifies evidence is present, not that it is true.
agent-check — questions
Answers built from our own checks of this server.