Agent Health is an MCP server with 21 tools an agent can call, among them agent_domain_challenge, agent_endpoint_assessment, agent_health_checks. It answers at https://autonet.work/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 12 September 2026; the last check, on 24 October 2026, succeeded.
Free owned-agent uptime monitoring, DNS domain proof, signed alerts and opt-in endpoint checks.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
agent_domain_challenge | 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. Inputs: agent_id, api_key |
agent_endpoint_assessment | 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. Inputs: agent_id, api_key, consent |
agent_health_checks | Read recent HTTP/TLS results to diagnose failures. Limit 1–500. Inputs: agent_id, limit |
agent_health_feed | 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. Inputs: agent_id |
agent_health_heartbeat | 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. Inputs: agent_id, api_key |
agent_health_instructions | Read FIRST: purpose, endpoint ownership requirements, heartbeat setup, scoring limits, API and free service usage. |
agent_health_status | Read public operational status and nested trust score. Provisional score is null; not identity/safety certification. Inputs: agent_id |
agent_webhook_secret | Owner-only retrieve webhook signing secret, or rotate it when explicitly requested. Keep the secret private. Inputs: agent_id, api_key, rotate |
create_callback_inbox | 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. Inputs: api_key, request_key, max_coins |
create_utility_account | Create a free utility account once; immediately save the returned private API key. 100 welcome coins. No billing or health registration. |
delete_agent_health | Permanently remove an owned registration and probe history when the operator requests it. Admin request logs retain up to 30 days. Inputs: agent_id, api_key |
delete_callback_inbox | Delete an owned inbox and all its events immediately. Its receive URL stops working. No coin refund; usage ledger remains. Inputs: api_key, inbox_id |
internet_utils_catalog | Get current coin costs and resource limits before spending. Paid usage and invoices are disabled in the beta. |
internet_utils_instructions | Read the free coin allowance, callback workflow, privacy limits and API usage. No health endpoint required. |
list_callback_inboxes | List your unexpired callback inboxes and receive URLs. Keep these addresses private to authorized senders. Inputs: api_key |
probe_me_now | 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. Inputs: agent_id, api_key |
read_callback_events | 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. Inputs: api_key, inbox_id, after |
register_agent_health | 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 endpo Inputs: name, endpoint_url, check_interval_sec, heartbeat_enabled, checks_config |
update_agent_health | Owner-only update. Pause when retiring/testing; resume with paused=false. Endpoint and webhook must be public URLs you control. Inputs: agent_id, api_key, paused, endpoint_url, check_interval_sec, heartbeat_enabled |
utility_account | Read your private coin balance and usage ledger. Requires a utility key, not a health owner key. Inputs: api_key |
verify_agent_domain | 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. Inputs: agent_id, api_key |
Every block below points at https://autonet.work/mcp. Pick your client and copy.
claude mcp add --transport http agent-health https://autonet.work/mcp
{
"mcpServers": {
"agent-health": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://autonet.work/mcp"]
}
}
}{
"mcpServers": {
"agent-health": {
"url": "https://autonet.work/mcp"
}
}
}{
"servers": {
"agent-health": {
"type": "http",
"url": "https://autonet.work/mcp"
}
}
}{
"context_servers": {
"agent-health": {
"url": "https://autonet.work/mcp"
}
}
}{
"mcpServers": {
"agent-health": {
"serverUrl": "https://autonet.work/mcp"
}
}
}{
"mcpServers": {
"agent-health": {
"url": "https://autonet.work/mcp"
}
}
}name: Agent Health
version: 0.0.1
schema: v1
mcpServers:
- name: Agent Health
type: streamable-http
url: https://autonet.work/mcp{
"mcpServers": {
"agent-health": {
"httpUrl": "https://autonet.work/mcp"
}
}
}{
"mcpServers": {
"agent-health": {
"type": "http",
"url": "https://autonet.work/mcp"
}
}
}{
"mcpServers": {
"agent-health": {
"url": "https://autonet.work/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fautonet.work%2Fmcp&type=streamable_http&id=agent-health&name=Agent%20Health
It answered our last check on 24 October 2026 in 373 ms. Over 6 checks since 12 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by autonet.work and served from autonet.work, the vendor's own domain: https://autonet.work/mcp.
21, as returned by the server's own tools/list on 23 September 2026: agent_domain_challenge, agent_endpoint_assessment, agent_health_checks, agent_health_feed, agent_health_heartbeat, agent_health_instructions, agent_health_status, agent_webhook_secret, and 13 more.
It answered our last check on 24 October 2026 in 373 ms. Over 6 checks since 12 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://autonet.work/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: work.autonet. Endpoint host: autonet.work. ARD identifier: urn:air:work.autonet:mcp:agent-health.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.