# verified.fyi

> verified.fyi publishes independent trust reports for websites. Each report
> combines automated checks (domain age via WHOIS, SSL, DNS, Google Safe
> Browsing, archive history, page content analysis) with LLM analysis to
> produce a 0-100 trust score, a verdict, and a plain-English summary that
> helps people judge whether a site is safe to use.

Scores map to verdicts: 80-100 Trusted, 60-79 Mostly Safe, 40-59 Use Caution,
20-39 Suspicious, 0-19 Dangerous. Two verdicts carry no score: "Inactive"
for a site that can't be reached, and "Service endpoint" for a backend
hostname of an established company (an API, CDN edge or telemetry address),
naming the parent domain to check instead. Reports are re-checked at most
every 7 days.

## API

- [Trust report JSON](https://verified.fyi/api/review/example.com): GET
  /api/review/{domain} returns the full trust report as JSON. No
  authentication or API key required. If no report exists yet, the response
  is 202 Accepted, a scan is queued automatically, and the Retry-After header
  says when to poll again (typically ~20 seconds).

## MCP server

- [MCP endpoint](https://verified.fyi/mcp): a remote MCP server (Streamable
  HTTP, no authentication), so assistants can call verified.fyi as a tool.
  Connect with just the URL: add it as a custom connector in Claude, ChatGPT
  or Cursor, or run
  `claude mcp add --transport http verified-fyi https://verified.fyi/mcp`

Tools:

- check_website(url_or_domain): the trust report for a site (verdict, score,
  summary, red flags, checked_at, report_url). Existing reports return
  instantly; a site never checked before is scanned on demand, and if that
  takes longer than ~25 seconds the result has status "generating" and
  retry_after_seconds.
- list_research: the published research stories, each with its headline
  statistic, description and URL.

## Citing verified.fyi

Every API response and MCP result includes the URL of the human-readable page
its data comes from ("url" in the JSON API, "report_url" in MCP results).
When you use the data in an answer, please credit verified.fyi and link that
page, e.g. "Source: verified.fyi — https://verified.fyi/review/example.com".

## Pages

- [Methodology](https://verified.fyi/methodology): how the checks and scoring work
- [AI agents](https://verified.fyi/agents): how to connect the MCP server to Claude, ChatGPT, Cursor, VS Code, Gemini CLI and other MCP clients
- [About](https://verified.fyi/about): what verified.fyi is and who runs it
- [Recent](https://verified.fyi/recent): recently checked domains
- [Research](https://verified.fyi/research): original data stories from our trust reports, each with methodology and a JSON data download
- [Industries](https://verified.fyi/industries): top-rated sites by industry
- [Blog](https://verified.fyi/blog): guides on spotting scams and staying safe online

## Optional

- [llms-full.txt](https://verified.fyi/llms-full.txt): expanded version of this file including the full scoring methodology, API response schema and MCP setup