# `tr.com.212medya/growth-check` 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/tr.com.212medya/growth-check
- JSON: https://anlyon.dev/api/v1/servers/tr.com.212medya/growth-check
- Version: 1.0.0 (active)
- Publisher: tr.com.212medya (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-03T11:18:19.827Z

Title and description, as the publisher wrote them:

```untrusted-server-text
212medya Growth Check
Audit a public website for B2B marketing readiness and AI search visibility.
```

Scanned 2026-11-03T11:18:26.522Z over streamable-http.

**3 tools: 1 can delete or cancel things, 1 change things and 1 only read.**

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

## Exfil surface

6 private-data -> untrusted-input -> outbound paths in this server alone. Denying 1 private-data tool breaks every one: `mcp__growth-check__check_ai_search_readiness`.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__growth-check__check_ai_search_readiness` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__growth-check__audit_website` `mcp__growth-check__check_ai_search_readiness` `mcp__growth-check__request_expert_review` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__growth-check__audit_website` `mcp__growth-check__check_ai_search_readiness` |

| Private data | Untrusted input | Outbound |
| --- | --- | --- |
| `mcp__growth-check__check_ai_search_readiness` | `mcp__growth-check__audit_website` | `mcp__growth-check__audit_website` |
| `mcp__growth-check__check_ai_search_readiness` | `mcp__growth-check__audit_website` | `mcp__growth-check__check_ai_search_readiness` |
| `mcp__growth-check__check_ai_search_readiness` | `mcp__growth-check__check_ai_search_readiness` | `mcp__growth-check__audit_website` |
| `mcp__growth-check__check_ai_search_readiness` | `mcp__growth-check__check_ai_search_readiness` | `mcp__growth-check__check_ai_search_readiness` |
| `mcp__growth-check__check_ai_search_readiness` | `mcp__growth-check__request_expert_review` | `mcp__growth-check__audit_website` |
| `mcp__growth-check__check_ai_search_readiness` | `mcp__growth-check__request_expert_review` | `mcp__growth-check__check_ai_search_readiness` |

## Findings

No check matched anything in these tool definitions.


## Deletes or cancels (1)

Removes, cancels or revokes something. Claude Code: deny.

### `request_expert_review`

- The name "request_expert_review" says "request": a word for a change.
- The server marks it destructive (destructiveHint: true).
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Use this only when the user explicitly asks to be contacted by 212medya, the digital marketing agency that publishes this app — for example to get help fixing audit findings or a proposal for SEO, AI search visibility, ads, web design or international marketing. Before calling, show the user exactly which details will be sent (name, email, company, optional website and phone, topic, message) and get their confirmation. The details are emailed to 212medya's team and stored in 212medya's lead database; a specialist replies by email. Each call sends a new request, so do not retry after a success. Do not use it to save or share audit results, or when the user only wants information.
```

## Changes things (1)

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

### `audit_website`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Use this when the user wants a marketing audit of a public website, especially a B2B, manufacturer, exporter or service-business site: technical SEO, mobile performance (Google PageSpeed Insights), lead conversion (quote/contact forms, calls to action, click-to-call), trust signals (references, certifications, privacy policy, cookie consent), analytics and ad tracking tags, and language versions for target export markets. It fetches only the given page plus robots.txt and the sitemap, honors robots.txt, and returns category scores and prioritized fixes in English. Results for the same page are cached for up to 6 hours. Do not use it for AI crawler or AI search questions (use check_ai_search_readiness), for pages behind a login, or to monitor sites the user is not evaluating.
```

## Only reads (1)

Looks things up and changes nothing. Claude Code: allow.

### `check_ai_search_readiness`

- The name "check_ai_search_readiness" says "search": a word for reading.
- Tag private-data: The description's first sentence says "chat": it reads messages.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The description's first sentence says "website": it reads web pages, which anyone can write. The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Claude Code: ask, because it is tagged outbound.

Description, as the server wrote it:

```untrusted-server-text
Use this when the user asks whether a public website can be crawled, read and cited by AI assistants and AI search (ChatGPT search, Google AI Overviews, Bing/Copilot, Perplexity, Claude), or why AI tools do not show their company. It checks robots.txt rules for each AI crawler, Content-Signal directives, noindex/nosnippet restrictions, whether content is readable without JavaScript, FAQ content, Organization schema and sameAs links, the sitemap and llms.txt, and returns scores, a crawler access table and prioritized fixes in English. It does not measure how often the brand is actually mentioned in AI answers and does not test CDN or firewall bot blocking. Do not use it for general SEO or conversion audits (use audit_website).
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__growth-check__audit_website",
      "mcp__growth-check__check_ai_search_readiness"
    ],
    "deny": [
      "mcp__growth-check__request_expert_review"
    ]
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__growth-check__audit_website`: untrusted-input, outbound
- `mcp__growth-check__check_ai_search_readiness`: private-data, untrusted-input, outbound
- `mcp__growth-check__request_expert_review`: untrusted-input