Skip to main content

Anki MCP Server

A Model Context Protocol (MCP) server for integrating AI assistants with Anki, the popular spaced repetition flashcard software.

Features

This MCP server enables AI assistants to interact with Anki through the following tools:

Tools

  • get-collection-overview: Returns an overview of the Anki collection like available decks, available models and their fields

  • add-or-update-notes: Adds new notes or updates existing ones. Allows batch adding/updating multiple notes at once.

  • get-cards-reviewed: Get the number of cards reviewed by day

  • find-notes: Allows querying notes using the Anki searching syntax

  • find-cards: Find card IDs matching a query in Anki

  • suspend-cards: Suspend cards by their card IDs

  • unsuspend-cards: Unsuspend cards by their card IDs

Resources

  • anki://docs/search-syntax: Comprehensive reference guide for Anki's search query syntax. Includes basic operators, field searches, tags, decks, card states, properties, timing, IDs, custom data, and advanced query examples. This resource provides language-agnostic documentation useful for anyone constructing search queries with the find-notes or find-cards tools

Requirements

  • Anki must be installed and running
  • The AnkiConnect add-on must be installed in Anki and running
  • This MCP server uses uv. To install uv, follow the official instructions.

Installation

Install as a plugin to get both the MCP server and language learning skill in one step:

/plugin install anki-mcp

Manual setup for Claude Code

  1. Add the MCP server:

    claude mcp add anki -- uvx anki-mcp
    
  2. Optionally, copy the skill files from skills/ into your project's .claude/skills/ directory for language learning guidance.

Claude Desktop

  1. Open your Claude Desktop config file:

    • macOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%/Claude/claude_desktop_config.json
  2. Add anki-mcp to the mcpServers section:

    "mcpServers": {
      "anki": {
        "command": "uvx",
        "args": ["anki-mcp"]
      }
    }
    
  3. Restart Claude Desktop.

MCP server only

For other MCP-compatible clients, run the server directly:

uvx anki-mcp

Language Learning Skill

This plugin includes a complementary skill that provides best practices for creating effective language learning flashcards. When installed as a plugin, the skill is automatically available. The skill includes:

  • Recommended workflow for card creation
  • Card quality guidelines (length, content, cloze usage)
  • Note type variety recommendations
  • Examples of good vs bad cards
  • Proficiency level guidelines (CEFR A1-C2)

The MCP server works independently of the skill, so you can use it for any Anki workflow — not just language learning.

Metadata

Release files for anki-mcp 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for anki-mcp 0.2.0
File Size Uploaded Provenance
anki_mcp-0.2.0.tar.gz 47.5 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for anki-mcp 0.2.0
File Interpreter ABI Platform
anki_mcp-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 61.2 kB

Release files / anki_mcp-0.2.0.tar.gz

Download URL anki_mcp-0.2.0.tar.gz
Size 47.5 kB
Tags Source
SHA-256 checksum
How to use checksums
5cb0aba94b33286e3ed2b0446839419d69390b7be4f295598e94f3dc826bf2d1
BLAKE2b-256 checksum
How to use checksums
c77676b87e593ab3070cae5d9c23d670b316e96aba53ed862130ca950f1ac12d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.10.8 {"installer":{"name":"uv","version":"0.10.8","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / anki_mcp-0.2.0-py3-none-any.whl

Download URL anki_mcp-0.2.0-py3-none-any.whl
Size 13.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
24f5eec4af35d87afeb71fa15fdd7dbbba4f403194a465d9d24e4ddea51262f2
BLAKE2b-256 checksum
How to use checksums
a32a6219b4a7f6aba4837a37bfc7827cb28bc6d3c106f6588beee36b575311d7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.10.8 {"installer":{"name":"uv","version":"0.10.8","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for anki-mcp 0.2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page