# `tools.websitefeedback/website-feedback-tool` 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/tools.websitefeedback/website-feedback-tool
- JSON: https://anlyon.dev/api/v1/servers/tools.websitefeedback/website-feedback-tool
- Version: 0.1.2 (active)
- Publisher: tools.websitefeedback (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T18:55:14.165Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Website Feedback Tool
Read visual design reviews from live web pages: comments, CSS selectors, styles, console errors.
```

Scanned 2026-10-21T19:20:59.976Z over streamable-http.

**5 tools: 1 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 | 1 | 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__website-feedback-tool__get_latest_review` `mcp__website-feedback-tool__get_review` `mcp__website-feedback-tool__get_screenshot` `mcp__website-feedback-tool__list_reviews` `mcp__website-feedback-tool__open_review_link` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__website-feedback-tool__get_screenshot` `mcp__website-feedback-tool__open_review_link` |

## Findings

No check matched anything in these tool definitions.


## Changes things (1)

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

### `open_review_link`

- The name "open_review_link" says "open": a word for a change.
- 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.

Description, as the server wrote it:

```untrusted-server-text
Open a design review from a share link somebody sent you (a /r/<id>?t=… URL) and get its feedback as Markdown. Use this when the user pastes a review link rather than asking for their own reviews — the link carries its own access, so the review does not need to have been pushed from this machine. It stays out of list_reviews: to open it again later, use the link again.
```

## Only reads (4)

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

### `get_latest_review`

- The name "get_latest_review" says "get": a word for reading.
- Tag untrusted-input: The name "get_latest_review" says "get" and "review": it reads comments, which other people can write. The description's first sentence says "get" and "review": it reads comments, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
Get the most recent design review as Markdown feedback (comments, selectors, computed styles, console/network errors, screenshot URLs).
```

### `get_review`

- The name "get_review" says "get": a word for reading.
- Tag untrusted-input: The name "get_review" says "get" and "review": it reads comments, which other people can write. The description's first sentence says "get" and "review": it reads comments, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
Get one design review by id as Markdown feedback. Obtain the id from list_reviews.
```

### `get_screenshot`

- The name "get_screenshot" says "get": a word for reading.
- Tag untrusted-input: The description's first sentence says "view" and "comment": it reads comments, which other people 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
View a comment's screenshot inline (clients don't fetch image URLs themselves). Pass the reviewId and the comment id shown next to the screenshot in get_review.
```

### `list_reviews`

- The name "list_reviews" says "list": a word for reading.
- Tag untrusted-input: The name "list_reviews" says "list" and "review": it reads comments, which other people can write. The description's first sentence says "list" and "review": it reads comments, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
List your recent design reviews pushed from the Design Review browser extension (newest first): website, title, time, comment count and the reviewId to pass to get_review. Use this to pick which review to apply.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `website-feedback-tool`:

```json
{
  "permissions": {
    "allow": [
      "mcp__website-feedback-tool__list_reviews",
      "mcp__website-feedback-tool__get_latest_review",
      "mcp__website-feedback-tool__get_review"
    ],
    "ask": [
      "mcp__website-feedback-tool__open_review_link",
      "mcp__website-feedback-tool__get_screenshot"
    ],
    "deny": []
  }
}
```

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

- `mcp__website-feedback-tool__list_reviews`: untrusted-input
- `mcp__website-feedback-tool__get_latest_review`: untrusted-input
- `mcp__website-feedback-tool__get_review`: untrusted-input
- `mcp__website-feedback-tool__open_review_link`: untrusted-input, outbound
- `mcp__website-feedback-tool__get_screenshot`: untrusted-input, outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-10-22T15:14:31.503Z, unchanged since 2026-10-22T15:14:31.503Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://anlyon.dev/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 | `1` |
| 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://anlyon.dev/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

https://dfozgzaflbudvthtlhvn.supabase.co/functions/v1/mcp: tools/list returned 5 tools to an anonymous client, including open_review_link (write)
```