# `dev.spritefetch/spritefetch` 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/dev.spritefetch/spritefetch
- JSON: https://anlyon.dev/api/v1/servers/dev.spritefetch/spritefetch
- Version: 0.1.0 (active)
- Publisher: dev.spritefetch (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-23T15:17:43.463Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Spritefetch
Search and download free CC0 2D sprite sheets and tilesets for games.
```

Scanned 2026-10-23T15:19:27.658Z 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 outbound.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__spritefetch__download` `mcp__spritefetch__get_asset` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__spritefetch__download` `mcp__spritefetch__get_asset` |
| 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.

### `download`

- The description's first verb is "get": a word for reading.
- Tag private-data: The description's first sentence says "get" and "file": it reads files.
- Tag untrusted-input: The description's first sentence says "get" and "url": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
Get a verified, versioned download for one asset: the immutable file URL, its SHA-256, and the slicing data. Optionally returns the PNG inline. Verify the checksum after saving.
```

### `get_asset`

- The name "get_asset" says "get": a word for reading.
- Tag private-data: The description's first sentence says "get" and "file": it reads files.
- Tag untrusted-input: The description's first sentence says "get" and "url": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
Get the full record for one asset version: license and provenance, slicing (frames, animations, pivot) or tileset data, file URL, size, and SHA-256.
```

### `search`

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

Description, as the server wrote it:

```untrusted-server-text
Search Spritefetch for CC0 2D sprite sheets and tilesets. Returns license, checksum, and slicing data. Check license fields before shipping. When nothing matches, suggestions lists filters to drop and, clearly labeled, third-party AI sprite generators (not affiliated, not CC0).
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__spritefetch__search",
      "mcp__spritefetch__get_asset",
      "mcp__spritefetch__download"
    ],
    "ask": [],
    "deny": []
  }
}
```

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

- `mcp__spritefetch__get_asset`: private-data, untrusted-input
- `mcp__spritefetch__download`: private-data, untrusted-input