Koskamo

verified.fyi MCP

This MCP server allows AI assistants to check the trustworthiness of websites by retrieving automated trust scores, verdicts, and plain-English summaries based on domain age, SSL, DNS, and content analysis. It also provides access to published research stories.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

verified.fyi MCP logo, by verified.fyiVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by verified.fyi
MCP endpoint (Streamable HTTP)
https://verified.fyi/mcp
Vendor documentation

What you can do with it

  • Check if a website is trustworthy using a trust score and verdict
  • Retrieve plain-English summaries of site safety assessments
  • List published research stories with headline statistics

Source and maintenance

Vendor evidenceRegistry 1.0.0

Protocol and capabilities

Server
verified-fyi 1.0.0
MCP protocol
2025-06-18
Tools
2 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

verified.fyi publishes independent trust reports for websites. A report scores a site from 0 to 100 with a verdict (Trusted, Mostly safe, Use caution, Suspicious, Dangerous, or Inactive when the site can't be reached), based on automated checks such as domain age, TLS, DNS, Google Web Risk, VirusTotal, blocklists, customer reviews, web archive history and page content, weighed by an LLM. A score is a risk guide, not a guarantee. Backend hostnames of established companies (APIs, CDN edges, telemetry) are not scored: their verdict is Service endpoint, with parent_domain naming the domain to check instead. check_website returns the report for a domain, scanning the site on demand if it has never been checked. list_research returns verified.fyi's published research stories. Citation metadata: every result carries the URL of the public verified.fyi page its data comes from (report_url, or url for research) and an attribution line in the form "Source: verified.fyi — <report_url>". The data is published for reuse with credit to verified.fyi and a link to that page.

Tools

2 advertised

check_website — Check website trust
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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 history, page content), with a link to the full report that lists every check. Use it before visiting, buying from, signing up to, or entering personal or payment details on an unfamiliar site, or when someone asks whether a site, online shop, link or sender's domain is legitimate, safe or a scam. Accepts a bare domain or any URL. Known sites return instantly. A site never checked before is scanned on demand, which usually takes 20-60 seconds; if the scan isn't finished within about 25 seconds the result has status "generating" and retry_after_seconds.

check_website input schema
{
  "type": "object",
  "required": [
    "url_or_domain"
  ],
  "properties": {
    "url_or_domain": {
      "type": "string",
      "description": "The website to check: a bare domain such as example.com, or any URL on it. Only the hostname is assessed."
    }
  },
  "additionalProperties": false
}
check_website output schema
{
  "type": "object",
  "required": [
    "status",
    "domain",
    "report_url",
    "attribution"
  ],
  "properties": {
    "score": {
      "type": [
        "null",
        "integer"
      ],
      "maximum": 100,
      "minimum": 0,
      "description": "Trust score from 0 (dangerous) to 100 (trusted). Omitted for Inactive sites and service endpoints."
    },
    "domain": {
      "type": "string",
      "description": "The hostname that was checked."
    },
    "status": {
      "enum": [
        "complete",
        "generating",
        "rate_limited",
        "failed"
      ],
      "type": "string",
      "description": "complete: the report is included. generating: a first scan is running, call again after retry_after_seconds. rate_limited: no report exists and new scans are paused, retry after retry_after_seconds or open report_url in a browser. failed: the scan could not complete."
    },
    "summary": {
      "type": "string",
      "description": "Plain-English assessment of the site."
    },
    "verdict": {
      "type": "string",
      "description": "Trusted, Mostly safe, Use caution, Suspicious, Dangerous, Inactive (site unreachable), or Service endpoint (a backend address of parent_domain, not a website)."
    },
    "checked_at": {
      "type": "string",
      "description": "When the report was generated. Reports are refreshed at most every 7 days."
    },
    "report_url": {
      "type": "string",
      "description": "The full report on verified.fyi, listing every check behind the verdict."
    },
    "attribution": {
      "type": "string",
      "description": "Citation line for this data."
    },
    "parent_domain": {
      "type": "string",
      "description": "For a service endpoint, the established domain it belongs to. Check that domain for a trust verdict."
    },
    "retry_after_seconds": {
      "type": "integer",
      "description": "For generating and rate_limited: seconds to wait before calling again."
    }
  },
  "additionalProperties": false
}
check_website annotations
{
  "title": "Check website trust",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
list_research — List verified.fyi research
Advertised by the server during the last successful anonymous check.
Advertised read-only

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 date, and links to the story and its JSON dataset. Useful when someone asks for statistics or trends about scam, phishing or fraudulent websites, or wants citable data on online safety.

list_research input schema
{
  "type": "object",
  "additionalProperties": false
}
list_research output schema
{
  "type": "object",
  "required": [
    "stories",
    "attribution"
  ],
  "properties": {
    "stories": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "object",
        "required": [
          "title",
          "headline_stat",
          "description",
          "published",
          "url",
          "data_url"
        ],
        "properties": {
          "url": {
            "type": "string",
            "description": "The story on verified.fyi."
          },
          "title": {
            "type": "string"
          },
          "data_url": {
            "type": "string",
            "description": "The story's frozen dataset as JSON."
          },
          "published": {
            "type": "string",
            "description": "Publication date (YYYY-MM-DD)."
          },
          "description": {
            "type": "string"
          },
          "headline_stat": {
            "type": "string",
            "description": "The story's key finding."
          }
        },
        "additionalProperties": false
      }
    },
    "attribution": {
      "type": "string",
      "description": "Citation line for this data."
    }
  },
  "additionalProperties": false
}
list_research annotations
{
  "title": "List verified.fyi research",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
834 ms
95th percentile latency
834 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 834 ms · metadata changed · 2 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http verified-fyi-mcp https://verified.fyi/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add verified-fyi-mcp --url https://verified.fyi/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable verified-fyi-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "verified-fyi-mcp": {
      "url": "https://verified.fyi/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "verified-fyi-mcp": {
      "type": "streamableHttp",
      "url": "https://verified.fyi/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start verified-fyi-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "verified-fyi-mcp": {
      "type": "http",
      "url": "https://verified.fyi/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http verified-fyi-mcp https://verified.fyi/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "verified-fyi-mcp": {
      "url": "https://verified.fyi/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "verified-fyi-mcp": {
      "serverUrl": "https://verified.fyi/mcp"
    }
  }
}

Let your agent find its tools

Find servers like verified.fyi MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run verified.fyi MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing