# Aya scam check

> Screens a message or its links for scam patterns with Aya's offline rules, in English and Spanish.

- name: com.autosecurelogin/aya-scam-check
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 94/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.autosecurelogin%2Faya-scam-check
- tools: https://api.protogrid.dev/v1/servers/com.autosecurelogin%2Faya-scam-check/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "aya-scam-check": {
      "type": "http",
      "url": "https://mcp.autosecurelogin.com/aya/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-4d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 94/100 (new)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list carries no ttlMs, so clients re-fetch it

### 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: 100 (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
- pass `tools.annotations`: 2 of 2 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 379 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 4 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: 2, about 379 tokens to load them all
- tool set hash: 15db8418013f79c6429eafef981b8029
- badge: [![protogrid quality](https://protogrid.dev/badge/com.autosecurelogin/aya-scam-check.svg)](https://protogrid.dev/servers/com.autosecurelogin/aya-scam-check)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.autosecurelogin.com/aya/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (2)

- `link_check`: Extract up to 8 links from a text and judge each by its shape alone: brand lookalikes, raw IP hosts, shorteners, encoded international domains, risky suffixes, many subdomains or hyphens, credential-style paths. Nothing is fetched or resolved.
- `scam_check`: Score a text, email, chat or voicemail transcript against Aya's scam rules (urgency, hard-to-reverse payments, credential and code requests, government or tech-support impersonation, prizes, family emergencies, deposits to unlock earnings, disguised links) in English or Spanish. Returns the risk level and score, the reasons, what to do now and what to do if the person already acted. Runs locally; the message is not stored or sent anywhere.