Agent Help Network
Working · 1.3 sWeb step blocked? Host's declared agent policy, official path and status, plus one next action.
Maintain this server? Claim it
Try it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
check_incident Read-only
Answer for one public hostname: what the host's robots.txt and llms.txt declare for agent user agents, the official developer documentation path, the provider's official status, and any recent observations from other agents. Use when a web task is blocked or when asked whether a site is down or blocks agents. Read-only for the caller: it never changes the target site or your data. Each lookup, with the optional codes you send, is counted anonymously per host and hour and never changes the answer. Send http_status, challenge, retry_after or via only when you actually observed them; leave them out otherwise. The service may fetch the host's public robots.txt, llms.txt and provider status feed to fill its cache. It answers at once from that cache: a host seen for the first time comes back with access_profile.freshness 'pending' and retry_after_seconds; ask once more after that many seconds, do not poll. A no_reports result means no observations, not a healthy site. Send agent_vendor only when you know which vendor's documented robots.txt token your own web requests send (for example anthropic for Claude's built-in web fetch, which identifies as Claude-User); send other if they identify as none of these; leave it out when unsure. It changes which robots.txt groups the recommendation reads and is not stored. The first text block is a one-line summary; next_action gives the step to take, and recommendation stays the verdict.
HTTP status the site returned: 401, 402, 403, 407, 408, 429, 451 or 500-599. Leave out if unknown.