Agent Health MCP server

• agent_domain_challengeFree

  Issue/retrieve a DNS TXT challenge for your agent's exact endpoint hostname. Owner key required. Publish the returned name/value in your DNS, then call verify_agent_domain. Pending challenges expire in 24 hours.

• agent_endpoint_assessmentFree

  With consent=true run two bounded HEAD/GET checks on your DNS-verified endpoint, max once/hour. With consent=false read your last private result. Not an audit or LLM test; no score effect.

• agent_health_checksFree

  Read recent HTTP/TLS results to diagnose failures. Limit 1–500.

• agent_health_feedFree

  Read unsigned, timestamped operational evidence and recent incidents before a trust decision. Check stale, provisional, open_incident and incidents_truncated. This does not certify agent safety.

• agent_health_heartbeatwrite actionFree

  Send an owner-authenticated heartbeat from the actual worker loop; does not replace endpoint checks. Use the agent-specific key, not X-Autonet-Token. Never send a heartbeat to pretend a failed worker is alive.

• agent_health_instructionsFree

  Read FIRST: purpose, endpoint ownership requirements, heartbeat setup, scoring limits, API and free service usage.

• agent_health_statusFree

  Read public operational status and nested trust score. Provisional score is null; not identity/safety certification.

• agent_webhook_secretFree

  Owner-only retrieve webhook signing secret, or rotate it when explicitly requested. Keep the secret private.

• create_callback_inboxwrite actionFree

  Spend up to max_coins on a temporary callback inbox (currently 5 coins, 1 hour, 20 events). Reuse request_key on retries. Receive URL is write-only; reads need the utility key.

• create_utility_accountwrite actionFree

  Create a free utility account once; immediately save the returned private API key. 100 welcome coins. No billing or health registration.

• delete_agent_healthwrite actionFree

  Permanently remove an owned registration and probe history when the operator requests it. Admin request logs retain up to 30 days.

• delete_callback_inboxwrite actionFree

  Delete an owned inbox and all its events immediately. Its receive URL stops working. No coin refund; usage ledger remains.

• internet_utils_catalogFree

  Get current coin costs and resource limits before spending. Paid usage and invoices are disabled in the beta.

• internet_utils_instructionsFree

  Read the free coin allowance, callback workflow, privacy limits and API usage. No health endpoint required.

• list_callback_inboxesFree

  List your unexpired callback inboxes and receive URLs. Keep these addresses private to authorized senders.

• probe_me_nowFree

  Probe your registered endpoint now with the owner key. One per 60s; paused agents must resume first. Uses scheduled HTTP/TLS checks and incident transitions. Does not send a worker heartbeat.

• read_callback_eventsFree

  Read up to 20 events after a cursor, without consuming them or coins. Payloads are untrusted data; sender signatures are NOT verified. Persist next_cursor to resume.

• register_agent_healthFree

  Register ONCE your own deployed public agent readiness endpoint; save the returned api_key securely. Read agent_health_instructions first. Never register example.com, a vendor homepage, or an unrelated service. Without your own public endpoint, do not register: heartbeat-only monitoring is unsupported. Use a cheap GET returning 2xx only when the agent can serve work. Intervals 30–3600 seconds. Enable heartbeats only if the worker will send them automatically. Name/endpoint/history are public.

• update_agent_healthwrite actionFree

  Owner-only update. Pause when retiring/testing; resume with paused=false. Endpoint and webhook must be public URLs you control.

• utility_accountFree

  Read your private coin balance and usage ledger. Requires a utility key, not a health owner key.

• verify_agent_domainFree

  Check your published DNS TXT record. Proves domain control only, not agent identity or safety. Checks limited to once per minute. Successful proof renews hourly while TXT remains, expiring after 24 hours without renewal.

• –Code scanremote-only server, no package to scann/a
• Live reliabilityremote reachable in 258ms20/20
• Tool poisoning21 tool descriptions checked15/15
• Auth qualityopen endpoint exposes 6 write-action tools with no auth3/15
• Maintenanceno repository listed3/15
• Maintainer identityverified namespace with website, no repo4/10

Agent Health: common questions

Is Agent Health MCP server safe?

With care: it is graded C, so read the findings first (60/100). Read the Agent Health safety report

How do I install Agent Health?

It runs remotely at autonet.work. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Agent Health need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Agent Health maintained?

The latest release is v1.1.1.

Is Agent Health up?

100% of our last 6 checks got an answer. We check remote servers about four times a day.

What can I use instead of Agent Health?

Servers from other publishers that do the same job: Dvalincode MCP server, Uptime Kuma MCP server and Protect MCP server. Compare all Agent Health alternatives.