work.autonet/agent-health
work.autonet/agent-health · v1.1.1 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Free owned-agent uptime monitoring, DNS domain proof, signed alerts and opt-in endpoint checks.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 53 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 4 tool(s) can execute commands or delete data (delete_diagnostic_watch, delete_liveness_subscription, delete_agent_health, delete_callback_inbox). Require confirmation before the agent calls them. |
What was checked
- https://autonet.work/mcp: answers without auth
Public tools: assert_healthy, diagnose_http, diagnose_mcp, run_autonet_sandbox, set_utility_identity, wait_until_ready, wait_for_callback, read_readiness_jobs, cancel_readiness_job, publish_mcp_report, export_incident_evidence, configure_agent_reengagement, read_agent_reengagement, run_signed_diagnostic, create_diagnostic_watch, read_diagnostic_watches, update_diagnostic_watch, delete_diagnostic_watch, agent_presence_history, agent_signed_evidence, evidence_signing_keys, subscribe_liveness, read_liveness_events, delete_liveness_subscription, request_monthly_credits, create_funding_checkout, run_credit_diagnostic, network_identity, send_heartbeat, get_agent_status
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/work-autonet-agent-health-53ef2c24)