Connects AI assistants to Anki through AnkiConnect for review, notes, decks, tags, media, and scheduling.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Anki MCP Server.
syncSync with AnkiWeb to pull latest data and push changes
get_due_cardsGet cards that are due for review, optionally filtered by deck (answers omitted unless `include_answer: true`, default `false`)
get_cardsGet cards with flexible filtering by state (due, new, learning, suspended, buried) and deck (answers omitted unless `include_answer: true`, default `false`)
present_cardShow a card for review with its question/front side
rate_cardRate card performance (Again, Hard, Good, Easy) and schedule the next review
forgetCardsReset cards to new, discarding their scheduling without recording a review
Anki MCP Server MCP server gives an AI assistant access to an Anki collection through AnkiConnect. It covers study workflows, collection maintenance, and content creation rather than only read-only lookup. Agents can synchronize with AnkiWeb, retrieve due or filtered cards, show a card front, record a review rating, and change suspension or scheduling state.
The server also supports deck and note operations. An agent can list or create decks, move cards, create notes individually or in batches, search notes with Anki query syntax, update fields, and delete notes with confirmation. Tag operations include adding, removing, replacing, and clearing unused tags.
Media tools list files in Anki's collection.media directory, retrieve files as base64, store files from base64, an absolute path, or a URL, and delete files. Model discovery is available through the modelNames tool, which helps an agent identify note types before creating notes.
Requests arrive through MCP and are translated into Anki operations through AnkiConnect. The sync operation pulls current data from AnkiWeb and pushes local changes. Review actions have different effects: rate_card records a performance rating and schedules the next review, while forgetCards resets a card to new without recording a review, and setDueDate changes its due timing without recording a review.
Card retrieval can be limited by deck and state, including due, new, learning, suspended, and buried. The get_due_cards and get_cards tools do not return answers unless include_answer is set to true. Note searches accept Anki query syntax such as deck:, tag:, and is:due.
Batch note creation supports up to 100 notes sharing a deck and model, with partial success possible. Deck creation supports a Parent::Child structure up to two levels. Destructive operations include deleting notes, removing media, and clearing unused tags.
The project documentation identifies AnkiConnect as the connection layer between the MCP server and Anki. The repository also publishes an npm package named @ankimcp/anki-mcp-server and identifies Claude Desktop in its documentation examples. The supplied material does not specify installation commands, required environment variables, transport settings, or AnkiConnect configuration steps.
Anki MCP Server MCP server is marked beta, so its APIs and features may change. Operations that delete notes, media, or unused tags are destructive. Card answers are hidden by default in the two card retrieval tools. The supplied material does not document authentication, supported operating systems, or client compatibility beyond the Claude Desktop example.
Factual signals from GitHub, npm, and our automated checks β not a rating.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/anki-mcp-server)<a href="https://allmcps.com/mcp/anki-mcp-server"><img src="https://allmcps.com/api/badge/anki-mcp-server?style=directory" alt="Anki MCP Server on AllMCPs" /></a>