# AI Website Security

> Security basics of a website: HTTPS certificate, redirection, headers, mixed content, DNS filtering.

- name: com.aiwebsitesecurity/ai-website-security
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 87/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.aiwebsitesecurity%2Fai-website-security
- tools: https://api.protogrid.dev/v1/servers/com.aiwebsitesecurity%2Fai-website-security/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ai-website-security": {
      "type": "http",
      "url": "https://scan.aiwebsitesecurity.com/api/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 87/100 (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 declares ttlMs 0, so clients re-fetch it on every use

### 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: 86 (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
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: check_site_security_basics (destructiveHint); get_security_offer (destructiveHint)
- pass `tools.token_cost`: about 407 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 3 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 407 tokens to load them all
- tool set hash: 4c44b73af50d8cc4b8041d60e52e3f9e
- badge: [![protogrid quality](https://protogrid.dev/badge/com.aiwebsitesecurity/ai-website-security.svg)](https://protogrid.dev/servers/com.aiwebsitesecurity/ai-website-security)
- 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://scan.aiwebsitesecurity.com/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (2)

- `check_site_security_basics`: Reads the public home page of a website as a visitor and returns the security basics: HTTPS certificate (validity, expiry date, host coverage, protocol), redirection from http to https, security headers (HSTS, CSP, X-Frame-Options, nosniff, Referrer-Policy, cookies), mixed content, and whether public DNS filtering resolvers (Cloudflare, Quad9) block the domain — a measured fact: part of the visitors cannot reach the site. It does not look for malware: that is the paid scan. Free; nothing is stored. Docs: https://aiwebsitesecurity.com/
- `get_security_offer`: Returns the AI Website Security offers — Record (malware and file-integrity scan with a signed report), Record + Restore (cleaning of the core files), Watch and Watch + Restore (daily watch for a year), Watch Fleet for agencies — with what each includes, its price, and the page where the site owner buys it (the owner accepts the terms and confirms ownership there). Docs: https://aiwebsitesecurity.com/tarifs