# `com.8b/ai-website-builder` 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.8b/ai-website-builder
- JSON: https://radar.anlyon.com/api/v1/servers/com.8b/ai-website-builder
- Version: 0.3.1 (active)
- Publisher: com.8b (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T17:47:30.836Z

Title and description, as the publisher wrote them:

```untrusted-server-text
8B AI Website Builder
AI website & landing page builder: animated site in an 8B design, preview, edits, HTML download
```

Scanned 2026-11-12T11:18:41.090Z over streamable-http.

**3 tools: 1 change things and 2 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 | 2 | allow |

## Exfil surface

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

| 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__ai-website-builder__generate_site` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

No check matched anything in these tool definitions.


## Changes things (1)

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

### `generate_site`

- The name "generate_site" says "generate": a word for a change.
- 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
Generates the user's site with 8B from a design and the texts, colors, fonts and photo queries written for the business, and shows a live, animated preview in the conversation. Call get_design_brief first to see the fields. Returns the preview id, the preview link and the link to download the site. To change a site that is already built (a color, some texts, a photo), call it with base_preview_id and only the values that change: everything else is kept.
```

## Only reads (2)

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

### `explore_designs`

- The description's first verb is "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Lists 8B site designs: the look, the structure and the kinds of business each one suits. Use it to choose the design for the user's site.
```

### `get_design_brief`

- The name "get_design_brief" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Returns the brief for writing the site in a design: every text with a hint and max length, the color palette, fonts and photos. Write them for the user's business and pass the values to generate_site.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__ai-website-builder__explore_designs",
      "mcp__ai-website-builder__get_design_brief"
    ],
    "ask": [
      "mcp__ai-website-builder__generate_site"
    ],
    "deny": []
  }
}
```

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

- `mcp__ai-website-builder__generate_site`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T18:33:04.170Z, unchanged since 2026-10-22T14:26:28.300Z. 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 | `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://radar.anlyon.com/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://mcp.8b.com/mcp: tools/list returned 3 tools to an anonymous client, including generate_site (write)
```
