# `io.github.j-doi/domain-bannin` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://anlyon.dev/servers/io.github.j-doi/domain-bannin
- JSON: https://anlyon.dev/api/v1/servers/io.github.j-doi/domain-bannin
- Version: 0.1.0 (active)
- Publisher: io.github.j-doi (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/j-doi/domain-shield
- Metadata from the official MCP Registry, synced 2026-10-21T18:36:30.531Z

Title and description, as the publisher wrote them:

```untrusted-server-text
ドメイン番人
ドメインの設定を調べる MCP サーバー。SPF / DKIM / DMARC・DNS・SSL 証明書・セキュリティヘッダ・サブドメイン・類似ドメインを、公開情報だけで確認します。登録不要・無料。
```

Scanned 2026-10-21T19:23:43.655Z over streamable-http.

**1 tool: 1 change things.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 1 | ask |
| Only reads | read | 0 | allow |

## Findings

No check matched anything in these tool definitions.


## Changes things (1)

Creates or changes something that can be changed back. Claude Code: ask.

### `domain_diagnose`

- The description's first verb is "run": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Runs a comprehensive health check on a public domain: SPF / DKIM / DMARC for the headline score, plus optional details on email-auth adjacent records (MX, BIMI, MTA-STS, TLS-RPT, DKIM key length), DNS infrastructure (NS, DNSSEC, CAA, AAAA, SOA, TXT), web security (HTTPS, certificate, HSTS, HTTP/2-3, CT log), domain registration (RDAP expiry, registrar lock, DS chain), and brand protection (typosquatting, TLD parity). Returns a structured report with per-category scores, individual diagnostic items, and a `critical_issues` cross-cut summary. No authentication required.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `domain-bannin`:

```json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__domain-bannin__domain_diagnose"
    ],
    "deny": []
  }
}
```