Skip to content
Verified logo

Verified MCP server

Which MCP servers are Verified's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-31

← Back to Verified

Whose server it is
  • Registry namefyi.verified/trust-reportsverified in the MCP registry

The registry name sits under verified.fyi. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-31
  • Stateanswerschecked 2026-10-31
  • Tools2
  • Server calls itselfverified-fyi
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-31 the server answered initialize and tools/list without a sign-in. First answer in 205 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: paste a website address to check its trust; read a plain-English safety verdict before sharing data.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "paste a website address to check its trust", the likely first call is check_website.
  • For "read a plain-English safety verdict before sharing data", the likely first call is check_website.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-31
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer778 ms
  • Space in an agent's context≈ 406 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results2 of 2 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · paste a website address to check its trust
  • can do · read a plain-English safety verdict before sharing data
  • not sure · compare a site's trust score against industry averages

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers2 tools · read 2026-10-31
  • check_website

    Look up verified.fyi's independent trust report for a website: a 0-100 trust score, a verdict and a plain-English summary, drawn from automated checks (domain age, TLS, DNS, Google Web Risk, VirusTotal, blocklists, reviews, archive…

  • list_research

    List verified.fyi's published research: original data stories built from its dataset of website trust reports, such as how a domain's age relates to scam risk. Each entry has the headline statistic, a short description, the publication…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "trust-reports": {
      "type": "http",
      "url": "https://verified.fyi/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http verified https://verified.fyi/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://verified.fyi/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.