
MCP server for Anki via AnkiConnect
MCP server for Anki via AnkiConnect
·
A Model Context Protocol (MCP) server that enables LLMs to interact with Anki flashcard software through AnkiConnect.
anki_check_connection - Check whether AnkiConnect is reachableanki_list_decks - List all available Anki decks, optionally with deck IDsanki_create_deck - Create a new Anki deckanki_list_tags - List all tags currently used in the collectionanki_add_note_tags - Add tags to one or more notesanki_remove_note_tags - Remove tags from one or more notesanki_create_note - Create a new noteanki_batch_create_notes - Create multiple notes at onceanki_search_notes - Search for notes using Anki query syntaxanki_get_note_info - Get detailed information about a noteanki_update_note - Update an existing note's fields and/or tagsanki_delete_note - Delete one or multiple notesanki_list_note_types - List all available note typesanki_create_note_type - Create a new note typeanki_get_note_type_info - Get detailed structure of a note typeanki_sync - Trigger AnkiWeb sync; requires {"confirm": true} because a full sync can merge or overwrite local and remote collections. Success means Anki accepted the request, not that AnkiWeb received the data; a blocking dialog in Anki can silently keep the sync queuedLegacy unprefixed tool names such as create_note and list_decks remain callable for existing clients, but new agent integrations should use the anki_* names.
anki://decks/all - Complete list of available decks with deck IDsanki://tags/all - Complete list of tagsanki://note-types/all - List of all available note typesanki://note-types/all-with-schemas - Detailed structure information for all note typesanki://note-types/{modelName} - Detailed structure information for a specific note typeThis repository supports Anthropic Desktop Extensions (MCPB). The easiest way to use this server in Claude Desktop is by installing the packaged .mcpb bundle.
.mcpb file locally using the provided script:npm run mcpb.mcpb file in, then click Install.This validates manifest.json and outputs a .mcpb archive you can install as above. Learn more about Desktop Extensions in Anthropic's announcement: Desktop Extensions: One-click MCP server installation for Claude Desktop.
Add the server to your claude_desktop_config.json:
{
"mcpServers": {
"anki": {
"command": "npx",
"args": ["--yes", "anki-mcp-server"]
}
}
}If your AnkiConnect is running on a different port, you can specify it using the --port parameter:
{
"mcpServers": {
"anki": {
"command": "npx",
"args": ["--yes", "anki-mcp-server", "--port", "8080"]
}
}
}Add the server to your Cline MCP settings file inside VSCode's settings cline_mcp_settings.json
{
"mcpServers": {
"anki": {
"command": "npx",
"args": ["--yes", "anki-mcp-server"]
}
}
}For Cline, you can also specify a custom port:
{
"mcpServers": {
"anki": {
"command": "npx",
"args": ["--yes", "anki-mcp-server", "--port", "8080"]
}
}
}Install the Anki skill to give Claude Code built-in knowledge of all Anki tools and workflows:
npx skills add nailuoGG/anki-mcp-server@ankiOnce installed, Claude Code will automatically use the skill when you ask it to create flashcards, manage decks, or batch import notes.
Note: Do not use the
.mcpbpackaged version as the MCP server — it outputs Electron metadata to stdout which breaks the MCP stdio protocol. Usenpx -y anki-mcp-serverinstead.
Create a distributable Desktop Extension bundle for Claude Desktop:
npm run mcpbThis will build the project and generate a .mcpb archive from the current repository, validating manifest.json. Test by dragging it into Claude Desktop's Extensions settings. Reference: Desktop Extensions: One-click MCP server installation for Claude Desktop.
This server is automatically published to the MCP Registry when a new version is released. The publishing process includes:
server.json file is validated against the MCP schema before publishingpackage.json, manifest.json, and server.jsonYou can validate the MCP server configuration locally:
npm run validate-mcpThis will download the latest MCP schema and validate your server.json file.
If you need to publish manually, you can use the MCP Publisher CLI:
# Install MCP Publisher
curl -L "https://github.com/modelcontextprotocol/registry/releases/download/v1.1.0/mcp-publisher_1.1.0_$(uname -s | tr '[:upper:]' '[:lower:]')_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz" | tar xz mcp-publisher
chmod +x mcp-publisher
sudo mv mcp-publisher /usr/local/bin/
# Login to MCP Registry
mcp-publisher login github-oidc
# Publish to MCP Registry
mcp-publisher publishnpm installnpm run buildnpm run watchRun the test suite:
npm testThis executes unit tests for MCP tool schemas, structured tool results, note creation, search/update/delete workflows, and error handling. These tests use mocked AnkiConnect clients; use MCP Inspector with a running Anki instance for manual integration checks.
Read-only agent evaluation assets live in evals/. Load the fixture into a disposable Anki profile, then run the XML questions against the MCP server to verify that agents can discover decks, tags, note type schemas, resources, and structured tool results.
Since MCP servers communicate over stdio, we recommend using the MCP Inspector:
npm run inspectorThis provides a browser-based interface for:
Create a new Anki deck called "Programming"Create an Anki card in the "Programming" deck with:
Front: What is a closure in JavaScript?
Back: A closure is the combination of a function and the lexical environment within which that function was declared.Create a cloze card in the "Programming" deck with:
Text: In JavaScript, {{c1::const}} declares a block-scoped variable that cannot be {{c2::reassigned}}.Delete note ID 1234567890Delete note IDs 1234567890, 9876543210, and 1122334455Add tags "review" and "mcp" to note IDs 1234567890 and 9876543210npm testIcon courtesy of macOS Icons
MIT License - see LICENSE file for details
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add anki -- npx --yes anki-mcp-server{
"mcpServers": {
"anki": {
"args": [
"--yes",
"anki-mcp-server"
],
"command": "npx"
}
}
}code --add-mcp '{"name":"anki","args":["--yes","anki-mcp-server"],"command":"npx"}'[mcp_servers.anki]
command = "npx"
args = ["--yes", "anki-mcp-server"]Runs locally on your device. Your client starts the server itself, so nothing has to be hosted.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/anki-mcp-server to learn what the "Anki MCP Server" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
npx skills add nailuoGG/anki-mcp-server@anki| Name | What it does |
|---|---|
anki_check_connection | Check whether AnkiConnect is reachable and return the API version. |
anki_list_decks | List all available Anki decks, optionally with deck IDs. |
anki_sync | Request AnkiWeb sync. Requires {"confirm": true}: without it the call is refused, because a full sync can merge or overwrite local and remote collections. Success means Anki accepted the request, not |
anki_create_deck | Create an Anki deck by name. |
anki_list_tags | List all tags currently used in the Anki collection. |
anki_add_note_tags | Use when the user wants to add one or more tags to existing notes for organization. Do not use when the user wants to remove tags (use anki_remove_note_tags) or update note content (use anki_update_no |
anki_remove_note_tags | Use when the user wants to remove specific tags from one or more existing notes. Do not use when the user wants to add tags (use anki_add_note_tags) or clear all tags (use anki_update_note with an emp |
anki_list_note_types | List all available Anki note types/models. |
anki_get_note_type_info | Use when inspecting a note type before creating or updating notes, especially for non-standard models. Returns fields and card templates. Call this before anki_create_note when using a custom note typ |
anki_create_note | Use when the user wants to create a single new study card (note) in an existing deck. Creates user study content — not a schema change. Do not use when the user only wants to inspect existing notes, d |
anki_batch_create_notes | Use when the user wants to create multiple study cards at once (2–50 notes). Prefer this over repeated anki_create_note calls. Returns per-note success and error details. Safety: ask the user to confi |
anki_search_notes | Search notes with Anki query syntax and return paginated note details. |
anki_get_note_info | Get detailed information for one note ID. |
anki_update_note | Use when the user wants to edit the fields or replace the tags of an existing note. Do not use when the user only wants to inspect note content (use anki_get_note_info) or delete it (use anki_delete_n |
anki_delete_note | Use when the user explicitly asks to permanently delete one or more notes. Do not use when the user only wants to inspect, search, or update notes. Safety: always confirm with the user before deleting |
anki_create_note_type | Use when the user wants to define a new note schema/model with custom fields and card templates. Modifies the Anki collection structure — not for creating study content. Do not use when the user wants |
| Name | What it does |
|---|---|
All Decks | List of all available decks in Anki |
All Tags | List of all tags used in Anki |
Read live from the server on September 29, 2026.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/anki-mcp-server)Nothing comparable is listed yet.
v0.2.5Release notesv0.2.4Release notesv0.2.3Release notesv0.2.2Release notesv0.2.1Release notesv0.2.0Release notesv0.2.0-beta.5Release notesv0.2.0-beta.4Release notesv0.1.8Release notesv0.1.5Release notesv0.1.4Release notesv0.1.3Release notesv0.1.2Release notesv0.1.1Release notes0.1.0v0.1.0Release notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "anki-mcp-server" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.