Skip to content

Verdict — Send anything. Get the truth.

by nrupala · remote · no sign-in to list tools · v1.1.0 · published by GitHub user nrupala

Send anything. Get the truth — REAL, SUSPICIOUS or LIKELY SCAM verdicts on messages and links.

Changes · 3
CompareRegistry entry

3 tools: 3 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http verdict https://verdict.aimlds.org/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 3Claude Code: ask
  • check_messagePaste any suspicious text — a message, email, marketplace listing, job offer, investment pitch or link — and get a plain verdict (REAL / SUSPICIOUS / LIKELY SCAM) with every check …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Paste any suspicious text — a message, email, marketplace listing, job offer, investment pitch or link — and get a plain verdict (REAL / SUSPICIOUS / LIKELY SCAM) with every check shown, a warning score, what to do next, a signed verdict certificate, and a shareable verdict link. Content is processed, not stored.
  • check_urlCheck one web link: it is followed safely server-side, tested for look-alike domains, domain age, sender rules, and the URLhaus known-bad list.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Check one web link: it is followed safely server-side, tested for look-alike domains, domain age, sender rules, and the URLhaus known-bad list. Returns the same verdict, checks, certificate and share link as check_message.
  • screen_urlsURL defense: screen up to 25 links in one call.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    URL defense: screen up to 25 links in one call. Each link is followed safely server-side and gets a verdict (REAL / SUSPICIOUS / LIKELY SCAM), a warning score, and its top warning flags. Private/internal links are refused per item and invalid entries are reported per item — one bad entry never fails the batch. One screen counts as one credit.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http verdict https://verdict.aimlds.org/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__verdict__check_message",
      "mcp__verdict__check_url",
      "mcp__verdict__screen_urls"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as verdict. Review it before you use it.