# anki_operations

Run general Anki utility operations: sync, version lookup, package import/export, profile listing, and media storage or retrieval. Use this for cross-cutting maintenance tasks that do not belong to flashcard, deck, model, or study workflows. Import, export, sync, and media writes have external side effects; version and profile reads do not. Select

Agent View of the PolicyLayer registry record for `anki_operations`. HTML page: https://policylayer.com/tools/io-github-arielbk-anki-mcp/anki-operations

## Facts

- Tool: `anki_operations`
- Server: Anki (`@arielbk/anki-mcp`) — https://policylayer.com/tools/io-github-arielbk-anki-mcp.md
- Install: `npx -y @arielbk/anki-mcp`
- Homepage: https://github.com/arielbk/anki-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "anki_operations",
    "arguments": {}
  }
}
```

## Why anki_operations is rated High

The tool executes commands that have external side effects (sync to Anki servers, import/export of data, media file writes), making it Execute rather than Write. It's not Destructive since operations are reversible (imports can be undone, syncs are not permanent overwrites). The high severity reflects that careless sync/import operations could corrupt user study data or cause unintended cloud synchronization.

From the tool's own definition: "Tool performs 'sync', 'import/export', 'media writes', and 'package' operations with external side effects. While framed as 'utility operations', these actions trigger side effects on Anki data stores and external systems."

## Use case

AI agents invoke anki_operations to trigger actions in Anki. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Anki:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "anki_operations": {
      "limits": [
        {
          "counter": "anki_operations_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Anki (97)

- `clear_unused_tags` — Destructive — https://policylayer.com/tools/io-github-arielbk-anki-mcp/clear-unused-tags.md
- `delete_decks` — Destructive — https://policylayer.com/tools/io-github-arielbk-anki-mcp/delete-decks.md
- `delete_media_file` — Destructive — https://policylayer.com/tools/io-github-arielbk-anki-mcp/delete-media-file.md
- `delete_notes` — Destructive — https://policylayer.com/tools/io-github-arielbk-anki-mcp/delete-notes.md
- `gui_exit_anki` — Destructive — https://policylayer.com/tools/io-github-arielbk-anki-mcp/gui-exit-anki.md
- `manage_decks` — Destructive — https://policylayer.com/tools/io-github-arielbk-anki-mcp/manage-decks.md
- `model_field_remove` — Destructive — https://policylayer.com/tools/io-github-arielbk-anki-mcp/model-field-remove.md
- `model_template_remove` — Destructive — https://policylayer.com/tools/io-github-arielbk-anki-mcp/model-template-remove.md
- `remove_deck_config` — Destructive — https://policylayer.com/tools/io-github-arielbk-anki-mcp/remove-deck-config.md
- `remove_empty_notes` — Destructive — https://policylayer.com/tools/io-github-arielbk-anki-mcp/remove-empty-notes.md
- `gui_answer_card` — Execute — https://policylayer.com/tools/io-github-arielbk-anki-mcp/gui-answer-card.md
- `gui_deck_browser` — Execute — https://policylayer.com/tools/io-github-arielbk-anki-mcp/gui-deck-browser.md
- `gui_deck_review` — Execute — https://policylayer.com/tools/io-github-arielbk-anki-mcp/gui-deck-review.md
- `gui_select_card` — Execute — https://policylayer.com/tools/io-github-arielbk-anki-mcp/gui-select-card.md
- `gui_select_note` — Execute — https://policylayer.com/tools/io-github-arielbk-anki-mcp/gui-select-note.md
- `gui_show_answer` — Execute — https://policylayer.com/tools/io-github-arielbk-anki-mcp/gui-show-answer.md
- `gui_show_question` — Execute — https://policylayer.com/tools/io-github-arielbk-anki-mcp/gui-show-question.md
- `gui_start_card_timer` — Execute — https://policylayer.com/tools/io-github-arielbk-anki-mcp/gui-start-card-timer.md
- `relearn_cards` — Execute — https://policylayer.com/tools/io-github-arielbk-anki-mcp/relearn-cards.md
- `reload_collection` — Execute — https://policylayer.com/tools/io-github-arielbk-anki-mcp/reload-collection.md
- `study_session` — Execute — https://policylayer.com/tools/io-github-arielbk-anki-mcp/study-session.md
- `api_reflect` — Other — https://policylayer.com/tools/io-github-arielbk-anki-mcp/api-reflect.md
- `card_reviews` — Other — https://policylayer.com/tools/io-github-arielbk-anki-mcp/card-reviews.md
- `export_package` — Other — https://policylayer.com/tools/io-github-arielbk-anki-mcp/export-package.md
- `gui_browse` — Other — https://policylayer.com/tools/io-github-arielbk-anki-mcp/gui-browse.md
- `gui_undo` — Other — https://policylayer.com/tools/io-github-arielbk-anki-mcp/gui-undo.md
- `multi` — Other — https://policylayer.com/tools/io-github-arielbk-anki-mcp/multi.md
- `request_permission` — Other — https://policylayer.com/tools/io-github-arielbk-anki-mcp/request-permission.md
- `sync` — Other — https://policylayer.com/tools/io-github-arielbk-anki-mcp/sync.md
- `cards_to_notes` — Read — https://policylayer.com/tools/io-github-arielbk-anki-mcp/cards-to-notes.md
- …and 67 more: https://policylayer.com/tools/io-github-arielbk-anki-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-arielbk-anki-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-arielbk-anki-mcp
