New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

Anki

98 tools. 70 can modify or destroy data without limits.

10 destructive tools with no built-in limits. Policy required.

Last updated:

70 can modify or destroy data
28 read-only
98 tools total

Community server · catalogue entry checked 01/08/2026

How to control Anki ↓

What Anki exposes to your agents

Read (28) Write / Execute (52) Destructive / Financial (10)
Critical Risk

The most dangerous Anki tools

70 of Anki's 98 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Anki

PolicyLayer is an MCP gateway — it sits between your AI agents and Anki, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "clear_unused_tags": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "add_note": {
    "limits": [
      {
        "counter": "add_note_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "cards_to_notes": {
    "limits": [
      {
        "counter": "cards_to_notes_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Anki — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON ANKI →

Instant setup, no code required.

All 98 Anki tools

WRITE 40 tools
Write add_note add_note Write add_notes add_notes Write add_tags_to_notes add_tags_to_notes Write answer_cards answer_cards Write can_add_notes can_add_notes Write change_deck change_deck Write clone_deck_config clone_deck_config Write create_deck create_deck Write create_model create_model Write find_and_replace_in_models find_and_replace_in_models Write forget_cards forget_cards Write gui_add_cards gui_add_cards Write gui_edit_note gui_edit_note Write gui_import_file gui_import_file Write import_package import_package Write insert_reviews insert_reviews Write manage_flashcards Create, update, delete, search, inspect, and tag Anki flashcards through one high-level note/card workflow. Us Write manage_models List, create, and modify Anki note types, including fields, templates, and CSS styling. Use this for schema/te Write model_field_add model_field_add Write model_field_rename model_field_rename Write model_field_reposition model_field_reposition Write model_field_set_description model_field_set_description Write model_field_set_font model_field_set_font Write model_field_set_font_size model_field_set_font_size Write model_template_add model_template_add Write model_template_rename model_template_rename Write model_template_reposition model_template_reposition Write remove_tags_from_notes remove_tags_from_notes Write replace_tags_in_notes replace_tags_in_notes Write save_deck_config save_deck_config Write set_card_specific_values set_card_specific_values Write set_cards_due_date set_cards_due_date Write set_cards_ease_factors set_cards_ease_factors Write set_deck_config set_deck_config Write store_media_file store_media_file Write suspend_cards suspend_cards Write unsuspend_cards unsuspend_cards Write update_model_styling update_model_styling Write update_model_templates update_model_templates Write update_note update_note

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Anki

Can an AI agent delete data through the Anki MCP server? +

Yes. The Anki server exposes 10 destructive tools including clear_unused_tags, delete_decks, delete_media_file. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Anki? +

The Anki server has 40 write tools including add_note, add_notes, add_tags_to_notes. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Anki.

How many tools does the Anki MCP server expose? +

98 tools across 4 categories: Destructive, Execute, Read, Write. 28 are read-only. 70 can modify, create, or delete data.

How do I enforce a policy on Anki? +

Register the Anki MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Anki tool call.

Deterministic rules across all 98 Anki tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

98 Anki tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Anki's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.