Runs a local MCP server inside Anki so Claude or other LLM clients can create, search, edit, move and study your cards conversationally, plus analyze retention.
Alternatives to AnkiMCP
AnkiWeb addon 1513864660
AI answer
Answers are generated by Claude from the catalog data and may contain mistakes.
Similar addons (found without AI)
Runs a local MCP server inside Anki so AI assistants can create cards, quiz you, search and manage decks live, with an optional public tunnel for remote access.
Adds an all-in-one study workspace with study plans, deadlines, Pomodoro timer, notebook, PDF viewer, mind maps, AI assistant, gamified XP, ranks, streaks, and themes.
Combines PDFs, EPUBs, videos, web pages, and notes with normal flashcards in incremental study sessions, letting you highlight, extract new cards, prioritize, and resume where you left off.
Provides a customizable statistics dashboard showing review activity, success rates, study patterns, heatmaps, streaks and due forecasts, with deck filters, themes and local multilingual support.
Turns Anki review data into a private local dashboard for progress, forecasts, deck health, FSRS insights, and safe, undoable search-based card and note maintenance.
Adds collapsible sidebars to Anki featuring AI card assistance, to-do lists, notes, exam countdowns, timers, a stopwatch, and quick filtered-deck creation for medical study.
Ranks First Aid Step 1 subjects and subtopics from weakest to strongest by Anki-style retention, showing sortable read-only dashboards and CSV export.
Simulates exam conditions through filtered-deck custom study sessions and reports performance metrics including total score, accuracy, time taken and grade.
Backs up add-on IDs via a synced deck and local add-on folders to WebDAV for restoration, optionally syncing selected decks to a self-hosted MCP knowledge base.
Estimates how long today's Anki reviews will take and tracks live progress, pace, and remaining time across all decks based on recent average review times.
Predicts remaining study time and finish time using an offline machine-learning model, with customizable progress displays, metrics, CSS styling, and fatigue alerts.