# `io.github.Ranqint/atelier-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.Ranqint/atelier-tools
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.Ranqint/atelier-tools
- Version: 1.0.0 (active)
- Publisher: io.github.Ranqint (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-12T19:17:37.557Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Atelier Studio Website Tools
Plan and score the website of an architecture or interior design studio.
```

Scanned 2026-11-12T19:18:17.280Z over streamable-http.

**2 tools: 1 change things and 1 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 | 1 | 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__atelier-tools__plan_studio_website_pages` |
| 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.

### `score_studio_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.

Description, as the server wrote it:

```untrusted-server-text
Scores an architecture or interior design studio website out of 100 from 14 yes / partly / no checks (project pages, plans and drawings, photography, the studio and services pages, ways to start a project, phone layout, share previews), and returns the fixes ordered by how much each one matters, plus a written website brief. Use when someone wants their studio or portfolio website reviewed. Send the answers that are known; the checks still unanswered come back with their wording, and the score appears once all 14 are answered.
```

## Only reads (1)

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

### `plan_studio_website_pages`

- The description's first verb is "list": a word for reading.
- Tag untrusted-input: The name "plan_studio_website_pages" says "website": it reads web pages, which anyone can write. The description's first sentence says "list" and "website": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
Lists the pages an architecture or interior design studio website needs, in the order a client meets them, with what goes on each page, plus the section-by-section structure of a project page. Use when an architect, interior designer or their web designer asks what pages a studio website should have, how to structure a portfolio, or what a project page should include.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__atelier-tools__plan_studio_website_pages"
    ],
    "ask": [
      "mcp__atelier-tools__score_studio_website"
    ],
    "deny": []
  }
}
```

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

- `mcp__atelier-tools__plan_studio_website_pages`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T18:21:37.690Z, unchanged since 2026-11-13T11:19:37.551Z. 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://atelier-tools.elya-studio.com/mcp: tools/list returned 2 tools to an anonymous client, including score_studio_website (write)
```
