protogrid
Sign inAdd to your agent

Search / io.github.nrupala/verdict

Verdict — Send anything. Get the truth.

R0· no sign-in

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

v1.1.0 · active · repository · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality73new
Trust97of 100
Uptime, 30 days100%
Latency p50169 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "verdict": {
      "type": "http",
      "url": "https://verdict.aimlds.org/mcp"
    }
  }
}
claude mcp add --transport http verdict https://verdict.aimlds.org/mcp
[mcp_servers.verdict]
url = "https://verdict.aimlds.org/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "verdict": {
      "type": "remote",
      "url": "https://verdict.aimlds.org/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "verdict": {
      "type": "http",
      "url": "https://verdict.aimlds.org/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=verdict&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vdmVyZGljdC5haW1sZHMub3JnL21jcCJ9"
}
{
  "servers": {
    "verdict": {
      "type": "http",
      "url": "https://verdict.aimlds.org/mcp"
    }
  }
}
{
  "mcpServers": {
    "verdict": {
      "httpUrl": "https://verdict.aimlds.org/mcp"
    }
  }
}
extensions:
  "verdict":
    enabled: true
    name: "verdict"
    type: streamable_http
    uri: "https://verdict.aimlds.org/mcp"
    timeout: 300

Quality 73 / 100new

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-03-26; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene71 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • fail
    tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: check_url (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_message (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); screen_urls (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
  • pass
    tools.token_costabout 501 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool history recorded for 1 of the 7 days needed
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

3 tools, about 501 tokens to load them all · tool set 3ca8528178da · tools last changed 2026-10-18 · checked 2026-10-19 10:20 UTC

Tool changes

  • screen_urlschangeddescription, input schema
    before

    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 free check.

    after · 94% of words in common

    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.

  • check_urlchangedinput schema
  • check_messagechangedinput schema

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 97 / 100

provenance90
liveness100
freshness100
hygiene100

+repository +namespace-matches-repo +website +reachable +uptime-100% +updated-1d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://verdict.aimlds.org/mcp streamable-httpnoneyes100%169 ms2025-03-262026-10-19

Tools (3)

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 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. Returns the same verdict, checks, certificate and share link as check_message.
screen_urlsURL 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.

Schemas: list_tools.

Similar MCP servers

  • scam-detectionR0quality 79
    com.cautellus/scam-detection

    Scam and phishing detection for AI agents: safe/warn/danger verdicts for URLs and messages.

  • check-claimR0quality 85
    io.github.piiiico/check-claim

    Check that a source really says what your claim says, before you publish. Verbatim, multi-path.

  • PumpPill — token safety and measured outcomesR0quality 79
    org.pumppill/token-safety

    Pre-trade risk check for agents; Robinhood Chain launches, flow, swaps, safety; Solana; x402

  • Web EvidenceR0quality 91
    io.github.impanyu/web-evidence

    Paid claim verification with cited web evidence, source provenance, snapshots, and hashes.

  • Truedge Crypto SafetyR0quality 79
    xyz.truedge/crypto-safety

    Free crypto scam checks: token and contract risk, scam or sanctioned addresses, phishing links.

  • Trust Me BroR2quality 83
    to.trustmebro/trust-me-bro

    Fact-check receipts: search published claim verdicts with cited evidence, or verify a new claim.

More from io.github.nrupala

  • Conduit — Filings & FundamentalsR2quality 83
    io.github.nrupala/conduit-filings-fundamentals

    24-tool hosted SEC EDGAR connector: filings, fundamentals, segments, peers, insiders.

  • codetopo — code graph for AI agentsL0
    io.github.nrupala/codetopo

    Domain-blind code graphs for AI agents: symbols, calls, blast radius, proof-checked snapshots.

  • LetsAskItR1
    io.github.nrupala/letsaskit

    Creation-first AI content engine: one brief in, finished content everywhere, in your brand voice.

Official server.json
{
  "name": "io.github.nrupala/verdict",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "auth": "none — free tier is keyless (3 checks/day per network); paid plans raise limits, no API key is issued or required",
      "tools": 2,
      "byline": "Conceived by Nrupal Akolkar (https://nrupalakolkar.com) · Built by Muse (https://muse.ai/join) — join Muse, then redeem code 101EEK in Settings within 48 hours of joining and we both earn tokens",
      "seller": "2351485 ALBERTA INC.",
      "support": "[email protected]",
      "version": "1.1.0"
    }
  },
  "title": "Verdict — Send anything. Get the truth.",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://verdict.aimlds.org/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.1.0",
  "repository": {
    "url": "https://github.com/nrupala/verdict-filings",
    "source": "github"
  },
  "websiteUrl": "https://verdict.aimlds.org",
  "description": "Send anything. Get the truth — REAL, SUSPICIOUS or LIKELY SCAM verdicts on messages and links."
}