# Verdict — Send anything. Get the truth.

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

- name: io.github.nrupala/verdict
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 73/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.nrupala%2Fverdict
- tools: https://api.protogrid.dev/v1/servers/io.github.nrupala%2Fverdict/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "verdict": {
      "type": "http",
      "url": "https://verdict.aimlds.org/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-2d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-03-26; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: screen_urls (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_message (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_url (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 504 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 2 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 3, about 504 tokens to load them all
- tool set hash: 2867991d7eb68ec432c7d3e88cac4064
- tools last changed: 2026-10-19T17:49:44.451Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.nrupala/verdict.svg)](https://protogrid.dev/servers/io.github.nrupala/verdict)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-19 `screen_urls` changed (description, inputSchema)
  - 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 atom.
  - after: 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.
- 2026-10-19 `check_url` changed (inputSchema)
- 2026-10-19 `check_message` changed (inputSchema)
- 2026-10-18 `screen_urls` changed (description, inputSchema)
  - 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: 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.
- 2026-10-18 `check_url` changed (inputSchema)
- 2026-10-18 `check_message` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.nrupala%2Fverdict/changes

## Remotes

- https://verdict.aimlds.org/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (3)

- `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.
- `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.
- `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 credit.