Verdict — Send anything. Get the truth.

io.github.nrupalaPublished by GitHub account nrupalav1.1.0Updated Oct 25, 2026

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

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingSecurity & Monitoring

Overview

AI-generated overview

A hosted MCP server that checks suspicious messages and links and returns a plain REAL, SUSPICIOUS or LIKELY SCAM verdict with the checks shown.

What you can do
Check a suspicious text, email, listing, job offer or investment pitch and get a verdict, warning score, next steps, a signed certificate and a share link (check_message). Check a single link, followed safely server-side, for look-alike domains, domain age, sender rules and known-bad lists (check_url). Screen up to 25 links in one call, with per-item refusals for private or internal addresses and per-item error reporting (screen_urls).
When to use it
Useful when an assistant is asked to judge whether a message, offer or link looks like a scam, phishing attempt or fraud, and the user wants the reasoning and evidence rather than a bare yes or no.
Requirements
A remote streamable-HTTP endpoint; no authentication or API key is needed for the free tier, which is limited to 3 checks per day per network. Paid tiers are bought through Stripe on the product site.
Before you install
Pasted content is sent to a third-party service operated by 2351485 ALBERTA INC.; the README says content is processed, not stored, and share links exclude the pasted content. Verdicts are described as likely, not guarantees. Paid tiers cost $6 or $12 USD per month, and the Family tier shows the payer a summary of likely scams found by household members.

Installation

In SourceWeft

  1. Open Verdict — Send anything. Get the truth. in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.nrupala%2Fverdict/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "verdict-send-anything-get-the-truth": {
      "type": "http",
      "url": "https://verdict.aimlds.org/mcp"
    }
  }
}

README

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: [email protected].

Connect

Client config

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

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

Tools (2)

ToolWhat it does
check_messageCheck 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_urlCheck 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)

TierPriceChecksFor
Free—3/daytrying it, the odd suspicious message
Pro$6 USD/mounlimitedone person — plus threat-intel checks and the signed verdict certificate on every check
Family$12 USD/mounlimited5 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.

Links

Conceived by Nrupal Akolkar · Built by Muse — join Muse, then redeem code 101EEK in Settings within 48 hours of joining and we both earn tokens.

Source: README.md at commit 7f7a190

Tools

3

check_message

Check a suspicious 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.

ParameterstextrequiredsubscriptionCode

check_url

Check a suspicious link

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.

ParametersurlrequiredsubscriptionCode

screen_urls

Screen a list of links

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.

ParametersurlsrequiredsubscriptionCode

Version history

1
  1. v1.1.0LatestOct 18, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts