Checks a public website in six areas and returns scores from 0 to 100. Free, no key needed.
Scored across 1 tool
The server exposes exactly one tool, so there is no possibility of misselection or overlapping purpose. An agent can immediately tell what it does and when to call it.
The single name 'website_check' uses a clean snake_case verb_noun pattern that matches the server's purpose. There is nothing to be inconsistent with.
The server is deliberately single-purpose (check one public website), so one tool earns its place rather than being a thin or arbitrary surface. It is still minimal, with no batch or retrieval variant, which keeps it just short of ideal.
For the narrow stated purpose — run a check on one public URL and return a summarized score — the surface is complete, including error paths, quotas, caching and terms. Minor gaps remain: no per-area or detailed per-check query, no batch/multi-URL check, and the full result is pushed off to an external website.
Checks one public website and returns a short result as Markdown: an overall score (0–100) with a band (good / medium / weak), the scores of six areas (speed & technology, findability, readiness for enquiries, trust & legal, website security settings, e-mail domain protection), one verdict line per area, how many checks per area were met, partly met, open, notes or not checkable, a short verdict, the address and time of the check, and the source line. The single checks with their measured values are not part of this result: the full result is free on https://www.rexity.ai/website-check. Use it when a user asks how a specific public website performs for visitors, search engines and enquiries. It states what was measured and gives no advice. The areas on security settings and e-mail domain protection use only what is visible from outside (response headers, one TLS handshake, public DNS, security.txt): not a security audit, no warranty. Only public http/https websites on standard ports; IP addresses, internal hosts and sites whose owners opted out are refused with a message that says why. A fresh check takes up to about a minute; results are cached for 24 hours. Quotas for fresh checks, currently: 5 per IP address and day, 200 per hour and 1000 per day for all callers together; calls that arrive from the shared addresses of an assistant platform count together, 300 per day for the platform; when a quota is reached the result says when it is restored. Terms of use: https://www.rexity.ai/website-check/nutzung. The checker identifies itself as RexityWebsiteCheck/1.0 (+https://www.rexity.ai/website-check/bot).
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The address of the website to check, for example www.example.de or https://www.example.de/. Public websites only. | |
| lang | No | Language of the result: de (German, default) or en (English). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes far beyond the readOnly/idempotent/openWorld annotations: it discloses latency (~1 minute for a fresh check), 24-hour caching, concrete quotas (5/IP/day, 200/hour, 1000/day global, 300/day per assistant platform, with restoration messaging), the identifying user-agent string, a terms-of-use link, and the explicitly limited methodology for the security and e-mail areas. This is unusually rich behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Purpose and result contents are front-loaded, and nearly every sentence carries distinct information (limits, refusals, quotas, disclaimers), so little is wasted. However, it is delivered as one dense run-on paragraph with minimal structural separation, which makes it harder to scan than a bulleted form would be.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, but the description fully specifies the return shape (score, band, six named areas, per-area verdicts, counts, timestamp, source line). Combined with the quota, caching and refusal behavior, an agent has everything needed to call it and interpret results.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and both parameters (url, lang) are already documented in the schema, including the de/en enum and default. The description adds no parameter-level syntax or format guidance, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Checks one public website') and enumerates exactly what the result contains: overall score with band, six area scores, per-area verdicts, counts of met/partly met/open/not-checkable, verdict, address, time, source line. No sibling tools exist, so no differentiation is needed and the purpose is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit when-to-use trigger: 'Use it when a user asks how a specific public website performs for visitors, search engines and enquiries.' It also states scope limits (only public http/https on standard ports; IP addresses, internal hosts and opted-out sites are refused with a reason) and clarifies it gives no advice and is not a security audit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
website_checkFree website analyzer: score any public URL 0-100 across 8 quality dimensions. No auth.
Check a deployed web app for security headers, SEO, accessibility and performance, with a grade.
Scores any public website on how usable it is by AI agents, with per-check evidence.
Free no-account URL security scan: 0-100 Launch Readiness score for any live site in ~15 seconds.
Add one secure layer between your agents and this server.