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 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 a hosted instance (e.g. a HuggingFace Space) by URL:

claude mcp add --transport http anki-addons https://<user>-anki-addons-mcp.hf.space/mcp

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, and query_sql (one sandboxed DuckDB SELECT over an addons table; only offered by SQL-capable backends).

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

Prompts: find_addon_for_task, compare_addons, addon_health_report, upgrade_readiness, monthly_ecosystem_digest, before_you_build, author_portfolio.

AI summaries 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).