Verdict — Send anything. Get the truth.

Official3 tools

by nrupala

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

io.github.nrupala/verdict — Model Context Protocol (MCP) Server

This MCP server provides verdicts for messages and links. It is described as a tool that returns results labeled as REAL, SUSPICIOUS, or LIKELY SCAM.

🛠️ Key Features

Sends input and returns a verdict
Verdict categories: REAL, SUSPICIOUS, LIKELY SCAM

🚀 Use Cases

Assess the credibility of messages
Evaluate whether links appear trustworthy or potentially fraudulent

⚡ Developer Benefits

Standardized verdict outputs for message/link assessment
Clear, constrained result set for downstream handling

⚠️ Limitations

Only the verdict labels and input/output purpose are described; no tool list, configuration, or API details are provided in the available source data.

Captured live from the server via tools/list.

check_message

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.

Parameters2

text	string	required	The full suspicious message or text to check (10–8000 characters).
subscriptionCode	string	optional	Optional subscription code (Personal Pro / Team). The check draws on the plan’s monthly atom allowance instead of the free daily atoms.

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The full suspicious message or text to check (10–8000 characters)."
    },
    "subscriptionCode": {
      "type": "string",
      "description": "Optional subscription code (Personal Pro / Team). The check draws on the plan’s monthly atom allowance instead of the free daily atoms."
    }
  },
  "required": [
    "text"
  ]
}

check_url

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.

Parameters2

url	string	required	The full link to check, starting with http:// or https://.
subscriptionCode	string	optional	Optional subscription code (Personal Pro / Team). The check draws on the plan’s monthly atom allowance instead of the free daily atoms.

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The full link to check, starting with http:// or https://."
    },
    "subscriptionCode": {
      "type": "string",
      "description": "Optional subscription code (Personal Pro / Team). The check draws on the plan’s monthly atom allowance instead of the free daily atoms."
    }
  },
  "required": [
    "url"
  ]
}

screen_urls

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 atom.

Parameters2

urls	array	required	The links to screen (1–25), each starting with http:// or https://.
subscriptionCode	string	optional	Optional subscription code (Personal Pro / Team). The screen draws on the plan’s monthly atom allowance instead of the free daily atoms.

Raw schema

{
  "type": "object",
  "properties": {
    "urls": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 25,
      "description": "The links to screen (1–25), each starting with http:// or https://."
    },
    "subscriptionCode": {
      "type": "string",
      "description": "Optional subscription code (Personal Pro / Team). The screen draws on the plan’s monthly atom allowance instead of the free daily atoms."
    }
  },
  "required": [
    "urls"
  ]
}

README.md3 KBView on GitHub

Verdict — MCP server (hosted)

Send anything. Get the truth.

Verdict checks anything suspicious — a text, an email, a marketplace listing, a job offer, an investment pitch, a link — and returns a plain verdict: REAL, SUSPICIOUS, or LIKELY SCAM, with every check shown in plain words and a clear "what to do next." Behind the verdict: links are followed safely on the server (private and internal addresses are refused before any fetch), look-alike and punycode domains are caught, domain age is read from the registry (RDAP), sender rules are checked (SPF/DMARC), known-bad lists are consulted, and the words themselves are scored for the pressure and payment tricks scams run on. Every check returns a signed verdict certificate and a shareable link that never contains the pasted content. Content is processed, not stored.

This repository is the public listing for the hosted Verdict MCP server: documentation and manifests only, no server source. The service is operated by 2351485 ALBERTA INC. Support: info@aimlds.org.

Connect

Endpoint: POST https://verdict.aimlds.org/mcp (streamable HTTP, stateless)
Auth: none — the free tier is keyless (3 checks/day per network)
Web: https://verdict.aimlds.org (paste anything, same verdict)
Email: forward any suspicious email to check@aimlds.org and get the verdict back by reply
Health: https://verdict.aimlds.org/health

Client config

Any MCP client that supports remote streamable-HTTP servers (Cline included):

json

{
  "mcpServers": {
    "verdict": {
      "url": "https://verdict.aimlds.org/mcp"
    }
  }
}

Tools (2)

Tool	What it does
`check_message`	Check any suspicious text — a message, email, listing, job offer, investment pitch or link — and get the verdict, every check, a warning score, what to do next, a signed verdict certificate, and a shareable verdict link
`check_url`	Check a single URL: it is followed safely server-side, its domain age and sender rules are read, and look-alike / known-bad checks run against it

Tiers (Stripe — live on the product site)

Tier	Price	Checks	For
Free	—	3/day	trying it, the odd suspicious message
Pro	$6 USD/mo	unlimited	one person — plus threat-intel checks and the signed verdict certificate on every check
Family	$12 USD/mo	unlimited	5 people on one family code, with a summary-only guard page that shows the payer every likely scam the household runs into

Verdicts say "likely," never a guarantee — the checks and their evidence are always shown so a person can judge for themselves.

Install

Tools (3)

check_messagecheck_urlscreen_urls

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://verdict.aimlds.org/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "verdict": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://verdict.aimlds.org/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

Verdict — Send anything. Get the truth.

io.github.nrupala/verdict — Model Context Protocol (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

check_message

check_url

screen_urls

Verdict — MCP server (hosted)

Connect

Client config

Tools (2)

Tiers (Stripe — live on the product site)

Links

Install

Remote endpoint

Related servers