Anki

40 tools. 21 can modify or destroy data without limits.

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

Last updated:

21 can modify or destroy data
19 read-only
40 tools total

Community server · catalogue entry verified 12/06/2026

How to control Anki ↓

What Anki exposes to your agents

Read (19) Write / Execute (17) Destructive / Financial (4)
Critical Risk

The most dangerous Anki tools

21 of Anki's 40 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
{
  "deleteDecks": {
    "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
{
  "removeTags": {
    "limits": [
      {
        "counter": "removetags_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "areSuspended": {
    "limits": [
      {
        "counter": "aresuspended_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 →

Free to start. No card required.

All 40 Anki tools

READ 19 tools
Read areSuspended Returns an array indicating whether each given card is suspended. Each item is boolean or null if the card doe Read cardsInfo Returns a list of objects containing information for each card ID provided. Read cardsModTime Returns modification time for each card ID provided. Result is a list of objects with Read cardsToNotes Returns an unordered array of note IDs for the given card IDs. Read deckNames Gets the complete list of deck names for the current user. Returns a list of deck names. Read deckNamesAndIds Gets the complete list of deck names and their respective IDs. Returns a dictionary mapping deck names to thei Read findCards Returns an array of card IDs for a given Anki search query. Read findModelsByName Gets a list of model definitions for the provided model names. Read findNotes Returns an array of note IDs for a given Anki search query. Read getDeckConfig Gets the configuration group object for the given deck name. Returns the deck configuration object. Read getMediaFilesNames Gets the names of media files matching the glob pattern. Returns a list of filenames. Read getNoteTags Gets the tags for a specific note ID. Returns a list of tags. Read modelFieldNames Gets the list of field names for the provided model name. Read modelNamesAndIds Gets the complete list of model (note type) names and their IDs. Returns a dictionary mapping model names to I Read modelStyling Gets the CSS styling for the provided model name. Returns an object containing the Read modelTemplates Returns an object indicating the template content for each card of the specified model. Read notesInfo Returns a list of objects containing information for each note ID provided. Read retrieveMediaFile Retrieves the base64-encoded contents of the specified media file. Returns the base64 string or false if not f Read suspended Checks if a single card is suspended by its ID. Returns true if suspended, false otherwise.

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 4 destructive tools including deleteDecks, deleteMediaFile, deleteNotes. 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 17 write tools including removeTags, changeDeck, storeMediaFile. 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? +

40 tools across 3 categories: Destructive, Read, Write. 19 are read-only. 21 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 40 Anki tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

40 Anki tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.