# `com.legendsoflearning.app/catalog` 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.legendsoflearning.app/catalog
- JSON: https://radar.anlyon.com/api/v1/servers/com.legendsoflearning.app/catalog
- Version: 1.0.0 (active)
- Publisher: com.legendsoflearning.app (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T17:58:05.442Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Legends of Learning
Search the Legends of Learning K-8 games catalog and standards alignment
```

Scanned 2026-11-13T16:17:48.724Z over streamable-http.

**3 tools: 3 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 0 | ask |
| Only reads | read | 3 | 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__catalog__legends_browse_standards` |
| 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.


## Only reads (3)

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

### `legends_browse_standards`

- The name "legends_browse_standards" says "browse": a word for reading.
- Tag untrusted-input: The name "legends_browse_standards" says "browse": it reads web pages, which anyone can write. The description's first sentence says "browse": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
Browses the public Legends of Learning curriculum taxonomy.

Without `standard_set`, lists the public standard sets (e.g. id "NGSS" for Next Generation Science Standards, "CCSS" for Common Core math), each with id, name, and subject_area; `query` filters them by name.

With `standard_set` (a set id from the list above), lists the standards in that set. Each standard has id, code (e.g. "2.OA.A.1" or an NGSS code), title, description, grades ("k" and "1"-"12"), and subject. Use a standard's id in legends_search_games' `learning_objective_ids` to find games aligned to it. `query` free-text matches code, title, and description; `grade` (integer, 0 = kindergarten) narrows to one grade level.

`page` (default 1) and `page_size` (default 10, max 25) paginate both modes.

Example: {"standard_set": "CCSS", "grade": 2, "query": "addition"} finds 2nd-grade Common Core standards about addition.

```

### `legends_get_game`

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

Description, as the server wrote it:

```untrusted-server-text
Fetches the full public detail for one Legends of Learning game by its numeric id (from legends_search_games).

Returns the game's id, title, description, image, estimated_duration in minutes, type, grades served, teacher/student ratings, instructions, vocabulary, discussion questions, capability flags (supports_ipad, supports_tts, multi_language, saves_progress), lexile_level, the public url, and `learning_objectives` — the standards the game is aligned to, each with id, title, code, and standard_set.

Example: {"game_id": 1445} returns that game, or an error result if no such game is publicly available.

```

### `legends_search_games`

- The name "legends_search_games" says "search": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Searches the public Legends of Learning game catalog (curriculum-aligned learning games for grades K-12 in math, science, and social studies).

Arguments (all optional): `query` free-text matches game titles and vocabulary; `grades` narrows to games for those grade levels (integers, 0 = kindergarten through 12); `game_type` is one of "instructional", "question", or "simulation"; `learning_objective_ids` narrows to games aligned to those learning objectives (get ids from legends_browse_standards); `page` (default 1) and `page_size` (default 10, max 25) paginate.

Returns `games` (each with id, title, description, image, estimated_duration in minutes, type, grades served, teacher/student ratings, and the game's public url) plus `page`, `page_size`, `total_entries`, and `total_pages`.

Example: {"query": "fractions", "grades": [3, 4], "page_size": 5} finds up to five 3rd-4th grade games about fractions.

```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__catalog__legends_search_games",
      "mcp__catalog__legends_browse_standards",
      "mcp__catalog__legends_get_game"
    ],
    "ask": [],
    "deny": []
  }
}
```

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

- `mcp__catalog__legends_browse_standards`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T18:41:41.233Z, unchanged since 2026-10-29T21:37:55.236Z. 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 | `0` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `https://app.legendsoflearning.com/.well-known/oauth-protected-resource` |
| Authorization servers | `https://app.legendsoflearning.com` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `yes` |
| Client ID metadata documents | `no` |

Posture changes:

- 2026-10-29T21:37:55.236Z: RFC 9728 protected resource metadata `none` -> `https://app.legendsoflearning.com/.well-known/oauth-protected-resource`; Authorization servers `none` -> `https://app.legendsoflearning.com`; Dynamic client registration `not observed` -> `yes`; Client ID metadata documents `not observed` -> `no`
