Check a URL before an agent clicks or cites it: status, redirects, dead/parked, phishing flags.
Scored across 1 tool
With only one tool exposed, there is no possibility of tool selection error — the agent can only call `preflight`. The description clearly states what the tool does and its boundaries (no page content extraction).
There is only one name, so there is no inconsistency to penalize. However, `preflight` does not follow the verb_noun convention seen in larger servers, leaving no stated pattern for future tools.
The server's scope is narrow and the single tool is rich (status, redirects, parked detection, content-type, llms.txt, abuse flags), which fits the purpose. Still, a one-tool surface is thin — sub-checks like reputation or robots.txt would naturally be separate operations.
For the preflight/URL-safety domain, coverage is broad: availability, redirect chain, dead/parked detection, metadata, llms.txt presence, and phishing signals. Minor gaps exist (no batch checking, no robots.txt/TLS detail), but agents can work around them.
Check a URL before you click, cite, or fetch it. Returns HTTP status, redirect chain and final URL, dead/parked-domain detection, content-type and size, whether /llms.txt exists, and phishing/abuse flags from public feeds plus heuristics. One call, no page content extraction. Free: 200 checks/day.
Inputs: url (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
URL reality check for agents: status, content hash, classification, wayback fallback.
Scan a URL before your agent reads it: hidden prompt injection, phishing, clean markdown.
Scan a URL before your agent reads it: hidden prompt injection, phishing, clean markdown.
Check a link, a message or a web page for scams and phishing before you or your agent act.
Add one secure layer between your agents and this server.