DevOps

autonet.work

Monitors deployed agents by registering health endpoints, tracking operational status and trust scores, running HTTP/TLS checks, and accepting owner-authenticated heartbeats from worker loops.

1 endpoint11 known toolsFirst detected September 10, 2026Last detected September 10, 2026

ENDPOINT 1

https://autonet.work/mcp

No auth detected

MCP server metadata

Name: Autonet Agent Health
Version: 1.30.0

Capabilities

experimentalpromptsresourcestools

Server instructions

Read agent_health_instructions first. Monitor only your own deployed readiness endpoint. Public reads and registration are free; owner write tools require the agent api_key. Names and User-Agent are self-reported.

Known tools 11

agent_health_instructions

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

Inferred read-only

register_agent_health

Inferred read-only

agent_health_status

Read public operational status and nested trust score.

Inferred read-only

agent_health_checks

Read recent HTTP/TLS results to diagnose failures.

Inferred read-only

agent_health_heartbeat

Send an owner-authenticated heartbeat from the actual worker loop; does not replace endpoint checks.

Potential side effects

update_agent_health

Owner-only update.

Potential side effects

delete_agent_health

Permanently remove an owned registration and probe history when the operator requests it.

Potential side effects

agent_domain_challenge

Issue/retrieve a DNS TXT challenge for your agent's exact endpoint hostname.

Inferred read-only

verify_agent_domain

Check your published DNS TXT record.

Inferred read-only

agent_webhook_secret

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

Inferred read-only

agent_endpoint_assessment

With consent=true run two bounded HEAD/GET checks on your DNS-verified endpoint, max once/hour.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.autonet-agent-health]
url = "https://autonet.work/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "autonet-agent-health": {
      "type": "http",
      "url": "https://autonet.work/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: autonet-agent-health
Remote MCP URL: https://autonet.work/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "autonet-agent-health": {
      "url": "https://autonet.work/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "autonet-agent-health": {
      "type": "http",
      "url": "https://autonet.work/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "autonet-agent-health",
  "transport": "streamable-http",
  "url": "https://autonet.work/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.