# `io.github.lazycipher/getbotrank-free-tools` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. 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://radar.anlyon.com/servers/io.github.lazycipher/getbotrank-free-tools
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.lazycipher/getbotrank-free-tools
- Version: 1.0.0 (active)
- Publisher: io.github.lazycipher (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/lazycipher/getbotrank-mcp
- Metadata from the official MCP Registry, synced 2026-11-08T05:17:40.855Z

Title and description, as the publisher wrote them:

```untrusted-server-text
GetBotRank Free AI Search Tools
Free, no-auth tools for AI search visibility: robots.txt, schema, rendering, sitemap, PageSpeed.
```

Scanned 2026-11-08T05:17:57.114Z over streamable-http.

**16 tools: 12 change things and 4 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 12 | ask |
| Only reads | read | 4 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | none |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__getbotrank-free-tools__check_common_crawl` `mcp__getbotrank-free-tools__preview_meta` `mcp__getbotrank-free-tools__view_as_crawler` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__getbotrank-free-tools__check_ai_crawler_access` `mcp__getbotrank-free-tools__check_entity` `mcp__getbotrank-free-tools__check_page_speed` `mcp__getbotrank-free-tools__check_redirects` `mcp__getbotrank-free-tools__check_rendering` `mcp__getbotrank-free-tools__generate_og_image` `mcp__getbotrank-free-tools__preview_meta` `mcp__getbotrank-free-tools__run_free_audit` `mcp__getbotrank-free-tools__score_citability` `mcp__getbotrank-free-tools__submit_indexnow` `mcp__getbotrank-free-tools__test_robots` `mcp__getbotrank-free-tools__validate_schema` `mcp__getbotrank-free-tools__view_as_crawler` |

## Findings

No check matched anything in these tool definitions.


## Changes things (12)

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

### `check_ai_crawler_access`

- The description's first verb is "request": a word for a change.
- 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
Request a page as GPTBot, ClaudeBot, PerplexityBot and other AI crawlers and compare with a normal browser to find robots.txt or CDN blocks.
```

### `check_common_crawl`

- Nothing in its name or description says what it does, so it is counted as a write.
- Tag untrusted-input: The name "check_common_crawl" says "crawl": it reads web pages, which anyone can write. The description's first sentence says "crawl": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
Check whether a domain appears in the latest Common Crawl crawls (a major source of LLM training data) and whether robots.txt blocks CCBot.
```

### `check_entity`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
Look up a brand on Wikidata and Wikipedia, report key properties, and check the site's Organization sameAs links.
```

### `check_page_speed`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
Google PageSpeed Insights for a URL: mobile and desktop Lighthouse scores, Core Web Vitals, CrUX field data when available, top opportunities.
```

### `check_redirects`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
Trace the redirect chain for a URL (max 10 hops) with status and timing per hop, plus X-Robots-Tag, HSTS, cache-control, content-type and canonical Link headers.
```

### `check_rendering`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
Estimate whether a page's content exists in the raw HTML before JavaScript runs (heuristic, no headless browser). Most AI crawlers do not execute JavaScript.
```

### `generate_llms_txt`

- The name "generate_llms_txt" says "generate": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Generate an llms.txt file for a domain from its sitemap (up to 40 pages in this MCP call).
```

### `generate_og_image`

- The name "generate_og_image" says "generate": a word for a change.
- 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
Resolve title, description and favicon for a 1200x630 Open Graph card from a URL or from text. Returns card data; render the PNG at the report_url.
```

### `run_free_audit`

- The name "run_free_audit" says "run": a word for a change.
- 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
Free AI readiness audit: crawlability, headings, structured data, llms.txt and metadata, scored 0 to 100.
```

### `score_citability`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
Score each passage of a page for how easily AI answer engines can quote it. Deterministic heuristics, no LLM.
```

### `submit_indexnow`

- The name "submit_indexnow" says "submit": a word for a change.
- Tag outbound: The input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Verify an IndexNow key file on a domain and, only if it verifies, submit up to 100 URLs to api.indexnow.org. Set action to "submit" to send URLs; the default only verifies.
```

### `test_robots`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
Test one URL against a site's robots.txt for 20+ crawlers (GPTBot, ClaudeBot, PerplexityBot, Googlebot, Bingbot and more) using correct longest-match rules. Returns allowed/blocked per bot with the deciding rule.
```

## Only reads (4)

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

### `preview_meta`

- The name "preview_meta" says "preview": a word for reading.
- Tag untrusted-input: 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
Read title, meta description, canonical, robots, Open Graph and Twitter tags with lengths, and return data for Google, LinkedIn, X and WhatsApp previews.
```

### `validate_schema`

- The name "validate_schema" says "validate": a word for reading.
- 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
Extract JSON-LD and microdata from a page, validate Organization, WebSite, Product, Article, FAQPage, BreadcrumbList, LocalBusiness and SoftwareApplication, and return a corrected JSON-LD block.
```

### `validate_sitemap`

- The name "validate_sitemap" says "validate": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Find and validate a domain's sitemaps, count URLs, status-check a sample of up to 50 URLs and check hreflang reciprocity.
```

### `view_as_crawler`

- The name "view_as_crawler" says "view": a word for reading.
- Tag untrusted-input: 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
Show the text and structure an AI crawler recovers from a page without running JavaScript.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `getbotrank-free-tools`:

```json
{
  "permissions": {
    "allow": [
      "mcp__getbotrank-free-tools__validate_sitemap"
    ],
    "ask": [
      "mcp__getbotrank-free-tools__test_robots",
      "mcp__getbotrank-free-tools__validate_schema",
      "mcp__getbotrank-free-tools__check_rendering",
      "mcp__getbotrank-free-tools__preview_meta",
      "mcp__getbotrank-free-tools__check_redirects",
      "mcp__getbotrank-free-tools__score_citability",
      "mcp__getbotrank-free-tools__generate_og_image",
      "mcp__getbotrank-free-tools__check_page_speed",
      "mcp__getbotrank-free-tools__check_common_crawl",
      "mcp__getbotrank-free-tools__check_entity",
      "mcp__getbotrank-free-tools__submit_indexnow",
      "mcp__getbotrank-free-tools__check_ai_crawler_access",
      "mcp__getbotrank-free-tools__view_as_crawler",
      "mcp__getbotrank-free-tools__generate_llms_txt",
      "mcp__getbotrank-free-tools__run_free_audit"
    ],
    "deny": []
  }
}
```

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

- `mcp__getbotrank-free-tools__test_robots`: outbound
- `mcp__getbotrank-free-tools__validate_schema`: outbound
- `mcp__getbotrank-free-tools__check_rendering`: outbound
- `mcp__getbotrank-free-tools__preview_meta`: untrusted-input, outbound
- `mcp__getbotrank-free-tools__check_redirects`: outbound
- `mcp__getbotrank-free-tools__score_citability`: outbound
- `mcp__getbotrank-free-tools__generate_og_image`: outbound
- `mcp__getbotrank-free-tools__check_page_speed`: outbound
- `mcp__getbotrank-free-tools__check_common_crawl`: untrusted-input
- `mcp__getbotrank-free-tools__check_entity`: outbound
- `mcp__getbotrank-free-tools__submit_indexnow`: outbound
- `mcp__getbotrank-free-tools__check_ai_crawler_access`: outbound
- `mcp__getbotrank-free-tools__view_as_crawler`: untrusted-input, outbound
- `mcp__getbotrank-free-tools__run_free_audit`: outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-15T13:20:58.222Z, unchanged since 2026-11-15T13:20:58.222Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `17` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **warn** Tools that change things, listed to anyone ([unauth-remote-writes](https://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 17 tools that change things (17 write). Whether a call also works without credentials was not tested: tools are never called.

https://api.getbotrank.com/mcp/free: tools/list returned 23 tools to an anonymous client, including test_robots (write), check_rendering (write), check_redirects (write), score_citability (write), generate_og_image (write) and 12 more
```

Posture changes:

- 2026-11-15T13:20:58.222Z: Tools that change things, listed without credentials `12` -> `17`
