# `com.sharelint/sharelint` 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/com.sharelint/sharelint
- JSON: https://radar.anlyon.com/api/v1/servers/com.sharelint/sharelint
- Version: 1.0.0 (active)
- Publisher: com.sharelint (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-11T10:17:42.336Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Sharelint
Check link previews in 12 apps, AI visibility for ChatGPT, Claude, Perplexity, and app links.
```

Scanned 2026-11-11T10:17:56.630Z over streamable-http.

**4 tools: 4 change things.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 4 | ask |
| Only reads | read | 0 | 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__sharelint__check_ai_visibility` `mcp__sharelint__check_app_links` `mcp__sharelint__check_link_preview` `mcp__sharelint__check_url` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__sharelint__check_ai_visibility` `mcp__sharelint__check_app_links` `mcp__sharelint__check_link_preview` `mcp__sharelint__check_url` |

## Findings

- **warn** Annotations that disagree with the tool in `check_link_preview` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "check_link_preview" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "check_link_preview" says "link": a word for a change.
```

- **warn** Annotations that disagree with the tool in `check_app_links` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "check_app_links" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "check_app_links" says "link": a word for a change.
```

- **warn** Annotations that disagree with the tool in `check_url` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "check_url" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
```


## Changes things (4)

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

### `check_ai_visibility`

- 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
Check whether ChatGPT, Claude, Perplexity and other AI search tools and assistants can reach, read and cite a URL. Evaluates robots.txt for each AI bot, requests the page with each bot’s User-Agent to catch CDN or firewall blocks, checks noindex, and shows the text an AI crawler gets from the raw HTML without JavaScript. Returns a score, per-bot access and copy-ready fixes. Use it for questions like "can ChatGPT see my site" or "why doesn’t Perplexity cite my page".
```

### `check_app_links`

- The name "check_app_links" says "link": a word for a change.
- 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.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Check whether a URL opens the site’s iOS or Android app instead of the browser. Validates apple-app-site-association (iOS Universal Links) and assetlinks.json (Android App Links), tests this exact URL against the iOS path rules, and compares the files with the copies Apple’s CDN and Google’s Digital Asset Links service have cached. Returns status per platform and copy-ready fixes. Use it when Universal Links or App Links do not work.
```

### `check_link_preview`

- The name "check_link_preview" says "link": a word for a change.
- 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.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Check how a URL’s link preview (title, description, image) appears when shared on WhatsApp, Facebook, Messenger, Instagram, X (Twitter), LinkedIn, Telegram, iMessage, Discord, Slack, Snapchat and TikTok. Fetches the page as each app’s crawler, validates Open Graph and Twitter Card tags and the preview image (size, format, weight), and returns a score, per-app results and copy-ready fixes. Use it when a shared link shows no preview, the wrong image or title, or before sharing a page.
```

### `check_url`

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

Description, as the server wrote it:

```untrusted-server-text
Run every Sharelint check on a URL at once: link previews in 12 apps, AI visibility for ChatGPT, Claude and Perplexity, and iOS and Android app links. Use it for a general "check my website or link" request; use the focused tools when the question is about one of these.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `sharelint`:

```json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__sharelint__check_link_preview",
      "mcp__sharelint__check_ai_visibility",
      "mcp__sharelint__check_app_links",
      "mcp__sharelint__check_url"
    ],
    "deny": []
  }
}
```

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

- `mcp__sharelint__check_link_preview`: untrusted-input, outbound
- `mcp__sharelint__check_ai_visibility`: untrusted-input, outbound
- `mcp__sharelint__check_app_links`: untrusted-input, outbound
- `mcp__sharelint__check_url`: untrusted-input, outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-19T17:21:34.924Z, unchanged since 2026-11-19T17:21:34.924Z. 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 | `7` |
| 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 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.

https://sharelint.com/api/mcp: tools/list returned 7 tools to an anonymous client, including check_link_preview (write), check_ai_visibility (write), check_seo (write), check_app_links (write), check_performance (write) and 2 more
```

Posture changes:

- 2026-11-19T17:21:34.924Z: Tools that change things, listed without credentials `6` -> `7`
