# `io.github.theluckystrike/mind-map` 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.theluckystrike/mind-map
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.theluckystrike/mind-map
- Version: 1.0.0 (active)
- Publisher: io.github.theluckystrike (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-08T03:18:01.867Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Zovo Mind Map
Turns an outline or a plan into a clean mind map you can print or download.
```

Scanned 2026-11-08T02:18:37.911Z over streamable-http.

**2 tools: 2 change things.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 2 | 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 or untrusted-input 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. | none |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

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

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

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


## Changes things (2)

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

### `generate_mind_map`

- The name "generate_mind_map" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Use this when the user wants a mind map, concept map, brainstorm map or topic tree drawn from an outline or a list of topics and subtopics, for example "turn these notes into a mind map" or "mind map of our launch plan". Takes an indented outline (2 spaces or 1 tab per level) or nested nodes, up to 300 topics and 6 levels, plus a layout (balanced, right-tree or org-down), a colour theme and a PDF page size. Returns the topic count, depth, main branches, an interactive map, and SVG, PDF and OPML downloads. Refuses mixed indentation and skipped levels with the line number. Does not draw flowcharts with decisions, timelines, images or links between branches, and does not save maps.
```

### `outline_from_mind_map`

- 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
Use this when the user wants a mind map turned back into a text outline, for example "give me this mind map as an outline" or "export the map as Markdown bullets". Takes the centre topic and nested nodes ({text, children}), up to 300 topics and 6 levels. Returns an indented or Markdown outline that generate_mind_map accepts again, the topic count and depth, and outline and OPML downloads. Does not read images of mind maps or files from other apps.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__mind-map__generate_mind_map",
      "mcp__mind-map__outline_from_mind_map"
    ],
    "deny": []
  }
}
```

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-15T13:24:50.179Z, unchanged since 2026-11-08T06:23:17.433Z. 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 | `2` |
| 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

https://mind-map.zovo.one/mcp: tools/list returned 2 tools to an anonymous client, including generate_mind_map (write), outline_from_mind_map (write)
```
