mcpwatch

← All servers

Grade B

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

SeverityRuleDetail
LowMW005Remote endpoint lists 53 tool(s) to anyone, no credentials needed.
MediumMW1024 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

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.

[![mcpwatch](https://www.mcpwatch.io/badge/work-autonet-agent-health-53ef2c24.svg)](https://www.mcpwatch.io/s/work-autonet-agent-health-53ef2c24)