Anki Addons MCP

An MCP server that gives LLM clients read-only access to the Anki Addons dataset: every addon in the AnkiWeb catalog, enriched with GitHub, Anki Forum and AI-summary and AI-tag data, published as monthly snapshots.

It answers questions such as "which addon does X?", "will it work on Anki 25.02?", "is it maintained?", and "what changed since last month?".

Links

• Anki Addons dataset on HuggingFace
• anki-addons-dataset, the pipeline that builds the dataset
• Developer Guide: running from sources, debugging, tests, architecture, deployment

Use it locally (STDIO)

Requires uv. uvx runs the PyPI package in an isolated, cached environment; to run a working copy instead, see Run from sources.

Register the server in Claude Code:

claude mcp add anki-addons -- uvx anki-addons-mcp

Other MCP clients use the same command (uvx anki-addons-mcp) in their server configuration, e.g.:

{
  "mcpServers": {
    "anki-addons": { "command": "uvx", "args": ["anki-addons-mcp"] }
  }
}

The first start downloads the latest snapshot (~15 MB) into the HuggingFace cache. Older snapshots are downloaded on demand by history tools, so the first history question can take a minute.

Use it remotely (Streamable HTTP)

Connect to the hosted instance on the HuggingFace Space by URL:

claude mcp add --transport http anki-addons https://ya-alex-anki-addons-mcp.hf.space/mcp

The Space sleeps after inactivity, so the first request can take a while. To explore the server in a browser, see Debug with the MCP Inspector.

To host your own instance, see Run over HTTP and Deploy to a HuggingFace Space.

Capabilities

Tools (all read-only, every data tool takes an optional snapshot, YYYY-MM-DD or latest): search_addons, filter_addons, get_addon, get_addon_readme, get_addon_description, check_compatibility, assess_maintenance, find_similar_addons, list_addons_by_author, get_addon_history, diff_snapshots, get_statistics, top_addons, list_snapshots, list_tags, and query_sql (one sandboxed DuckDB SELECT over the addons and tags tables; only offered by SQL-capable backends). search_addons accepts every filter of filter_addons (including AI tags with tags and exclude_tags) and combines them with the text query. Compatibility follows Anki's parsed versions (point versions and the hard/tested/open/unknown kind of the upper version); both tools filter by anki_version_kind and anki_version_at_least, and filter_addons also sorts by anki_version. list_addons_by_author takes a GitHub user, or an AnkiWeb author by author_id or by any of the author's addons (addon_id). AnkiWeb authors are derived by the dataset and are missing in snapshots collected before authors were tracked. get_addon_description returns plain text, or the author's unsanitized HTML with format=html.

Resources: anki-addons://dataset/readme, anki-addons://dataset/schema, anki-addons://dataset/anki-versions, anki-addons://snapshots, anki-addons://snapshots/{snapshot}/metadata, anki-addons://snapshots/{snapshot}/aggregation, anki-addons://addons/{addon_id} (and /readme, /description, /description.html, /history), anki-addons://authors/{github_user}, anki-addons://tags, anki-addons://tags/{tag}.

Prompts: find_addon_for_task, compare_addons, addon_health_report, upgrade_readiness, monthly_ecosystem_digest, before_you_build, author_portfolio, best_in_category, category_landscape, anki_release_readiness.

AI summaries and tags in the dataset are LLM-generated; the server labels them as such.

Configuration

CLI flags override environment variables (prefix ANKI_MCP_, also read from .env).