de en es ja ko ru zh

Anki MCP

Name: Anki MCP
Author: arielbk

by arielbk

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

🧠 Anki MCP

NPM-Paket yanki-connect Lizenz: MIT

Verwandeln Sie Ihr Anki-Karteikarten-Erlebnis mit KI! Dieser MCP-Server (Model Context Protocol) verbindet Ihre Anki-Karteikartensammlung mit KI-Assistenten wie Claude und ermöglicht so natürliche Gespräche über Ihre Lernmaterialien.

🚀 Was können Sie tun?

Stellen Sie sich vor, Sie hätten einen KI-Tutor, der Ihre gesamte Karteikartensammlung kennt und Folgendes kann:

📚 Interaktives Lernen

„Testen Sie mich mit japanischen Vokabeln, die ich seit drei Tagen nicht mehr gesehen habe.“
„Testen Sie mich mit anspruchsvollen Karten aus meinem Medizindeck“
„Zeigen Sie mir Karten, mit denen ich in letzter Zeit Probleme hatte.“

✨ Intelligente Inhaltserstellung

"Erstellen Sie Lernkarten zur Photosynthese mit Diagrammen"
„Verwandeln Sie dieses PDF-Kapitel in verteilte Wiederholungskarten.“
„Lückentext-Löschkarten aus meinen Vorlesungsmitschriften erstellen“

🔍 Leistungsstarke Analysen

„Mit welchen Themen habe ich am meisten zu kämpfen?“
„Zeigen Sie mir meine Lernmuster des letzten Monats“
„Wie hoch ist meine Bindungsrate für verschiedene Kartentypen?“

🎯 Massenvorgänge

„Tagge alle meine Chemiekarten mit ‚Prüfungsvorbereitung‘“
„Verschieben Sie Karten mit geringer Merkfähigkeit in ein intensives Wiederholungsdeck.“
„Finde und behebe doppelte Karten in meinen Decks“

Related MCP server: Anki MCP Server

🎯 Funktionen

Vollständige Anki-Integration : Vollständiger Zugriff auf Decks, Karten, Notizen und Statistiken über alle 115 AnkiConnect-API-Methoden
Konversationsschnittstelle : Natürliche Sprachbefehle über Ihren KI-Assistenten
Massenvorgänge : Verwalten Sie Tausende von Karten gleichzeitig effizient
Echtzeitstatistiken : Erhalten Sie Einblicke in Ihren Lernfortschritt
Medienunterstützung : Verarbeiten Sie Bilder, Audio und andere Medien auf Ihren Karten
Erweiterte Abfragen : Finden Sie Karten mithilfe komplexer Suchkriterien
Typsicherheit : Vollständig typisierte API mit umfassender Fehlerbehandlung

🛠 Technischer Stack

Node.js : Laufzeitumgebung (ab 18 Jahren erforderlich)
TypeScript : Typsicherheit und Entwicklererfahrung
MCP SDK : Implementierung des Model Context Protocol
yanki-connect : 🙏 Vollständig typisierter, isomorpher AnkiConnect-API-Client
tsup : Schneller TypeScript-Bündeler
PNPM : Effizienter Paketmanager

Besonderer Dank gilt der Yanki-Connect- Bibliothek für die Bereitstellung der robusten AnkiConnect-Schnittstelle, die diese Integration ermöglicht!

📋 Voraussetzungen

1. Anki installieren

Laden Sie Anki herunter und installieren Sie es, falls Sie dies noch nicht getan haben.

2. Installieren Sie das AnkiConnect-Plugin

Öffnen Sie Anki
Gehen Sie zu Extras → Add-ons
Klicken Sie auf „Add-ons abrufen …“
Code eingeben: 2055492159
Starten Sie Anki neu

📋 Versionsanforderungen: Dieser Server benötigt AnkiConnect Version 25.2.25.0 oder neuer (veröffentlicht am 25.02.2025) für volle Kompatibilität. Die meisten Funktionen funktionieren mit älteren Versionen, wir empfehlen jedoch ein Update für ein optimales Erlebnis.

3. AnkiConnect konfigurieren (optional)

AnkiConnect funktioniert sofort, Sie können die Einstellungen jedoch anpassen:

Gehen Sie zu Extras → Add-ons
Wählen Sie AnkiConnect und klicken Sie auf „Konfigurieren“
Die Standardeinstellungen sollten für die meisten Benutzer gut funktionieren

🚀 Schnellstart

Option 1: Verwendung mit Claude Desktop (empfohlen)

Installieren des Pakets
```
npm install -g @arielbk/anki-mcp
```
Claude Desktop konfigurieren
Bearbeiten Sie Ihre Claude Desktop-Konfigurationsdatei:
macOS : ~/Library/Application Support/Claude/claude_desktop_config.jsonWindows : %APPDATA%\Claude\claude_desktop_config.json
Fügen Sie diese Konfiguration hinzu:
```
{
  "mcpServers": {
    "anki": {
      "command": "anki-mcp",
      "args": []
    }
  }
}
```
Starten Sie Claude Desktop neu
Fangen Sie an, es zu verwenden!
- Stellen Sie sicher, dass Anki mit aktiviertem AnkiConnect ausgeführt wird
- Fragen Sie Claude: „Zeigen Sie mir meine Anki-Decks“ oder „Questieren Sie mich mit 5 Karten ab“

💡 Profi-Tipp: Sie können Ihr Setup testen, indem Sie Claude einfache Fragen stellen wie „Wie viele Anki-Decks habe ich?“ oder „Was ist in meinem größten Deck?“

Option 2: Entwicklungs-Setup

Klonen Sie das Repository

git clone https://github.com/arielbk/anki-mcp.git
cd anki-mcp

Abhängigkeiten installieren
```
pnpm install
```
Erstellen des Projekts
```
pnpm build
```

Testen des Servers

# Use the MCP inspector to test functionality
pnpm inspect

Option 3: Verwendung mit anderen MCP-Clients

Dieser Server funktioniert mit jedem MCP-kompatiblen Client. Sie können ihn auch verwenden mit:

MCP Inspector : Interaktives Debugging-Tool
Cline : VS Code-Erweiterung für KI-Codierung
Benutzerdefinierte MCP-Clients : Erstellen Sie Ihren eigenen mit dem MCP SDK

Führen Sie für den Stdio-Transport Folgendes aus:

node dist/index.js

🎮 Anwendungsbeispiele

Nach der Konfiguration mit Claude Desktop können Sie natürliche Gespräche führen wie:

📖 Lernsitzungen

You: "I have a Japanese exam tomorrow. Can you quiz me on Hiragana cards I haven't reviewed in a week?"

Claude: I'll find your Hiragana cards that need review and start a quiz session...

📝 Inhaltserstellung

You: "Create flashcards for the major battles of World War II with dates and significance"

Claude: I'll create comprehensive flashcards covering the key WWII battles...

📊 Studienanalyse

You: "How am I doing with my medical terminology deck? Show me my weak areas."

Claude: Let me analyze your performance on the medical terminology deck...

🏷️ Organisation

You: "Tag all cards about cardiovascular system with 'cardiology' and move them to my MCAT prep deck"

Claude: I'll help you organize those cards...

🔧 Verfügbare Tools und Ressourcen

Dieser MCP-Server bietet umfassenden Zugriff auf Ihre Anki-Sammlung durch diese Funktionen:

📚 Deckverwaltung

Liste aller Decks mit Statistiken
Neue Decks erstellen
Decks umbenennen und löschen
Deckkonfiguration abrufen

🗂️ Kartenoperationen

Karten anhand von Suchkriterien finden
Antwortkarten (Bewertungen simulieren)
Erhalten Sie Karteninformationen und Statistiken
Karten sperren/entsperren
Massenkartenvorgänge

📝 Notizverwaltung

Neue Notizen mit benutzerdefinierten Feldern hinzufügen
Vorhandene Notizen aktualisieren
Notizen löschen
Notizen per Suchanfrage finden
Massennotizvorgänge

📊 Statistiken & Analysen

Deckstatistiken und Leistungsmetriken
Kartenease- und Intervalldaten
Überprüfen Sie Verlauf und Muster
Einblicke in den Lernfortschritt

🎨 Medien & Models

Zugriffsnotiztypen und Felddefinitionen
Mediendateiverwaltung
Unterstützung für die Vorlagenanpassung

🔍 Erweiterte Funktionen

Komplexe Suchanfragen mit Ankis Suchsyntax
Stapelverarbeitung für mehr Effizienz
Echtzeitsynchronisierung mit Anki
Fehlerbehandlung und Validierung
Organisierte API-Methoden, gruppiert nach Funktionalität (Karten, Decks, Notizen, Modelle, Statistiken, Medien usw.)
Direkter Zugriff auf alle 115 AnkiConnect API-Methoden mit vollständiger Typsicherheit

🛠 Entwicklung

# Run in development mode with auto-reloading
pnpm dev

# Lint the code
pnpm lint

# Format the code
pnpm format

# Test with MCP inspector
pnpm inspect

🔧 Konfiguration

AnkiConnect-Einstellungen

Der Server verbindet sich standardmäßig mit AnkiConnect auf localhost:8765 . Wenn Sie Ihre AnkiConnect-Konfiguration angepasst haben, müssen Sie möglicherweise die Verbindungseinstellungen anpassen.

Wichtig : Stellen Sie sicher, dass Anki läuft und AnkiConnect installiert ist, bevor Sie den MCP-Server verwenden. Der Server kann keine Verbindung herstellen, wenn AnkiConnect nicht erreichbar ist.

💡 Hinweis: Die zugrunde liegende Yanki-Connect-Bibliothek unterstützt den automatischen Start von Anki unter macOS, diese Funktion ist jedoch derzeit nicht in der MCP-Serverkonfiguration verfügbar. Sie müssen Anki manuell starten.

Erweiterte Konfiguration von Claude Desktop

Für fortgeschrittene Benutzer können Sie zusätzliche Parameter übergeben:

{
  "mcpServers": {
    "anki": {
      "command": "anki-mcp",
      "args": ["--verbose"],
      "env": {
        "ANKI_CONNECT_HOST": "localhost",
        "ANKI_CONNECT_PORT": "8765"
      }
    }
  }
}

Fehlerbehebung

Häufige Probleme:

„Verbindung zu AnkiConnect fehlgeschlagen“ : Stellen Sie sicher, dass Anki ausgeführt wird und das AnkiConnect-Plugin installiert ist
„Keine Decks gefunden“ : Stellen Sie sicher, dass Sie mindestens ein Deck in Anki haben
Claude antwortet nicht : Starten Sie Claude Desktop nach Konfigurationsänderungen neu
Berechtigungsfehler : Überprüfen Sie, ob die globale npm-Installation mit npm list -g @arielbk/anki-mcp korrekt funktioniert hat

🤝 Beitragen

Wir freuen uns über Beiträge! Bitte:

Forken Sie das Repository
Erstellen eines Feature-Zweigs
Nehmen Sie Ihre Änderungen vor
Fügen Sie gegebenenfalls Tests hinzu
Senden einer Pull-Anfrage

📜 Lizenz

MIT – Einzelheiten finden Sie in der Datei LICENSE .

🙏 Danksagungen

yanki-connect – Ausgezeichneter TypeScript-Client für AnkiConnect
AnkiConnect – Das Plugin, das Anki-Automatisierung ermöglicht
Model Context Protocol – Ermöglicht nahtlose KI-Integrationen

Verwandeln Sie Ihr Karteikarten-Erlebnis mit KI-gestützten Konversationen! 🚀

Available Tools

7 tools

anki_operationsD

ParametersJSON Schema

Name	Required	Description
`operation`	Yes	Anki utility operation
`deckName`	No	Deck name to export
`filePath`	No	File path for export/import
`includeSched`	No	Include scheduling in export
`filename`	No	Media filename
`mediaData`	No	Base64 encoded media data
`mediaUrl`	No	URL to download media from
`pattern`	No	Pattern to match media files

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_analyticsD

ParametersJSON Schema

Name	Required	Description
`scope`	Yes	Analytics scope
`deckName`	No	Deck name for deck-specific stats
`cardIds`	No	Card IDs for detailed analysis
`startTimestamp`	No	Start timestamp for review history
`wholeCollection`	No	Get whole collection stats vs current deck

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_media_fileD

ParametersJSON Schema

Name	Required	Description	Default
`filename`	Yes	Media filename referenced in Anki cards (e.g., "image.png")

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

manage_decksD

ParametersJSON Schema

Name	Required	Description
`operation`	Yes	Deck management operation
`deckName`	No	Deck name
`deckNames`	No	Deck names (for batch operations)
`deleteCards`	No	Delete cards when deleting deck
`cardIds`	No	Card IDs to move
`targetDeck`	No	Target deck for moving cards
`configId`	No	Config ID to apply

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

manage_flashcardsD

ParametersJSON Schema

Name	Required	Description
`operation`	Yes	The flashcard operation to perform
`deckName`	No	Deck name (for create operations)
`modelName`	No	Note type/model name (for create operations)
`fields`	No	Field name-value pairs (for create/update)
`tags`	No	Tags to add/remove or set
`notes`	No	Array of notes to create (for create_batch)
`noteId`	No	Note ID (for update/delete single note)
`noteIds`	No	Note IDs (for delete multiple)
`query`	No	Anki search query (for find operation)
`includeDetails`	No	Include detailed note info (for find)
`limit`	No	Max results to return (default: 50, recommended to prevent context overflow)
`offset`	No	Number of results to skip for pagination (default: 0)
`cardIds`	No	Card IDs to get info for

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

manage_modelsD

ParametersJSON Schema

Name	Required	Description
`operation`	Yes	Model management operation
`modelName`	No	Model/note type name
`fields`	No	Field names in order (for create)
`templates`	No	Card templates (for create)
`css`	No	CSS styling
`isCloze`	No	Is cloze deletion type
`fieldName`	No	Field name
`newFieldName`	No	New field name (for rename)
`fieldIndex`	No	Field index position
`templateName`	No	Template name
`template`	No	Template content

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

study_sessionD

ParametersJSON Schema

Name	Required	Description
`operation`	Yes	Study session operation
`query`	No	Search query to find cards (for find_due)
`cardIds`	No	Card IDs to operate on
`answers`	No	Card answers (for answer operation)
`days`	No	Days from today for due date (for reschedule)

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

98 tool updatesv1.0.0Jan 3, 2026
- Removedadd_note
- Removedadd_notes
- Removedadd_tags_to_notes
- Addedanki_operations
- Removedanswer_cards
- Removedapi_reflect
- Removedcan_add_notes
- Removedcard_reviews
- Removedcards_to_notes
- Removedchange_deck
- Removedcheck_card_suspended
- Removedcheck_cards_due
- Removedcheck_cards_suspended
- Removedclear_unused_tags
- Removedclone_deck_config
- Removedcreate_deck
- Removedcreate_model
- Removeddelete_decks
- Removeddelete_media_file
- Removeddelete_notes
- Removedexport_package
- Removedfind_and_replace_in_models
- Removedfind_cards
- Removedfind_notes
- Removedforget_cards
- Removedget_active_profile
- Addedget_analytics
- Removedget_cards_ease_factors
- Removedget_cards_info
- Removedget_cards_intervals
- Removedget_cards_mod_time
- Removedget_collection_stats_html
- Removedget_latest_review_id
- Removedget_media_dir_path
- Addedget_media_file
- Removedget_media_files_names
- Removedget_num_cards_reviewed_by_day
- Removedget_num_cards_reviewed_today
- Removedget_profiles
- Removedget_reviews_of_cards
- Removedget_version
- Removedgui_add_cards
- Removedgui_answer_card
- Removedgui_browse
- Removedgui_check_database
- Removedgui_current_card
- Removedgui_deck_browser
- Removedgui_deck_overview
- Removedgui_deck_review
- Removedgui_edit_note
- Removedgui_exit_anki
- Removedgui_import_file
- Removedgui_select_card
- Removedgui_select_note
- Removedgui_selected_notes
- Removedgui_show_answer
- Removedgui_show_question
- Removedgui_start_card_timer
- Removedgui_undo
- Removedimport_package
- Removedinsert_reviews
- Removedload_profile
- Addedmanage_decks
- Addedmanage_flashcards
- Addedmanage_models
- Removedmodel_field_add
- Removedmodel_field_remove
- Removedmodel_field_rename
- Removedmodel_field_reposition
- Removedmodel_field_set_description
- Removedmodel_field_set_font
- Removedmodel_field_set_font_size
- Removedmodel_template_add
- Removedmodel_template_remove
- Removedmodel_template_rename
- Removedmodel_template_reposition
- Removedmulti
- Removedrelearn_cards
- Removedreload_collection
- Removedremove_deck_config
- Removedremove_empty_notes
- Removedremove_tags_from_notes
- Removedreplace_tags_in_notes
- Removedrequest_permission
- Removedretrieve_media_file
- Removedsave_deck_config
- Removedset_card_specific_values
- Removedset_cards_due_date
- Removedset_cards_ease_factors
- Removedset_deck_config
- Removedstore_media_file
- Addedstudy_session
- Removedsuspend_cards
- Removedsync
- Removedunsuspend_cards
- Removedupdate_model_styling
- Removedupdate_model_templates
- Removedupdate_note
91 tool updatesAug 15, 2025
- First observedadd_note
- First observedadd_notes
- First observedadd_tags_to_notes
- First observedanswer_cards
- First observedapi_reflect
- First observedcan_add_notes
- First observedcard_reviews
- First observedcards_to_notes
- First observedchange_deck
- First observedcheck_card_suspended
- First observedcheck_cards_due
- First observedcheck_cards_suspended
- First observedclear_unused_tags
- First observedclone_deck_config
- First observedcreate_deck
- First observedcreate_model
- First observeddelete_decks
- First observeddelete_media_file
- First observeddelete_notes
- First observedexport_package
- First observedfind_and_replace_in_models
- First observedfind_cards
- First observedfind_notes
- First observedforget_cards
- First observedget_active_profile
- First observedget_cards_ease_factors
- First observedget_cards_info
- First observedget_cards_intervals
- First observedget_cards_mod_time
- First observedget_collection_stats_html
- First observedget_latest_review_id
- First observedget_media_dir_path
- First observedget_media_files_names
- First observedget_num_cards_reviewed_by_day
- First observedget_num_cards_reviewed_today
- First observedget_profiles
- First observedget_reviews_of_cards
- First observedget_version
- First observedgui_add_cards
- First observedgui_answer_card
- First observedgui_browse
- First observedgui_check_database
- First observedgui_current_card
- First observedgui_deck_browser
- First observedgui_deck_overview
- First observedgui_deck_review
- First observedgui_edit_note
- First observedgui_exit_anki
- First observedgui_import_file
- First observedgui_select_card
- First observedgui_select_note
- First observedgui_selected_notes
- First observedgui_show_answer
- First observedgui_show_question
- First observedgui_start_card_timer
- First observedgui_undo
- First observedimport_package
- First observedinsert_reviews
- First observedload_profile
- First observedmodel_field_add
- First observedmodel_field_remove
- First observedmodel_field_rename
- First observedmodel_field_reposition
- First observedmodel_field_set_description
- First observedmodel_field_set_font
- First observedmodel_field_set_font_size
- First observedmodel_template_add
- First observedmodel_template_remove
- First observedmodel_template_rename
- First observedmodel_template_reposition
- First observedmulti
- First observedrelearn_cards
- First observedreload_collection
- First observedremove_deck_config
- First observedremove_empty_notes
- First observedremove_tags_from_notes
- First observedreplace_tags_in_notes
- First observedrequest_permission
- First observedretrieve_media_file
- First observedsave_deck_config
- First observedset_card_specific_values
- First observedset_cards_due_date
- First observedset_cards_ease_factors
- First observedset_deck_config
- First observedstore_media_file
- First observedsuspend_cards
- First observedsync
- First observedunsuspend_cards
- First observedupdate_model_styling
- First observedupdate_model_templates
- First observedupdate_note

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

D1.8/5.0

Scored 2026-04-18 10:00 across 7 tools

Disambiguation4/5

The tools have distinct purposes targeting different aspects of Anki functionality: operations, analytics, media, decks, flashcards, models, and study sessions. There is some potential overlap between 'anki_operations' and the more specific 'manage_' tools, but the separation is generally clear enough for an agent to distinguish them based on their names.

Naming Consistency3/5

The naming is mixed: 'anki_operations', 'get_analytics', and 'get_media_file' follow a verb_noun pattern, while 'manage_decks', 'manage_flashcards', and 'manage_models' use a verb_noun pattern with a consistent 'manage_' prefix, and 'study_session' is a noun_noun pattern. This inconsistency in conventions reduces predictability but remains readable.

Tool Count5/5

With 7 tools, the count is well-scoped for an Anki server, covering core areas like decks, flashcards, models, study sessions, analytics, media, and general operations. Each tool appears to earn its place without being excessive or insufficient for the domain.

Completeness3/5

The tool set covers key areas of Anki (decks, flashcards, models, study, analytics, media, operations), but without descriptions, it's unclear if there are gaps in CRUD/lifecycle coverage. For example, 'manage_flashcards' might imply create/update/delete, but specific tools for individual operations are missing, potentially leading to agent workarounds.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

Flash AOAuth
com.flashmemorize
Spaced-repetition flashcards your AI writes, quizzes you on by voice, and schedules with FSRS.
Education & Learning Tools Speech Processing
2412
Flashcards Open Source AppOAuth
com.flashcards-open-source-app
Read, write, and conversationally review open-source flashcards through split read/write MCP tools.
Education & Learning Tools Note Taking
229
Acornonaut MCP ServerOAuth
io.github.zerolve-io
AI-powered YouTube to flashcards with spaced repetition and Anki export
Education & Learning Tools AI & Machine Learning
2
Quizlar — voice-powered AI flashcards with spaced repetitionOAuth
io.github.quizlar
Voice-led, FSRS-scheduled flashcards from YouTube, PDFs, web, or text. Auto-graded quizzes.
Education & Learning Tools Speech Processing Knowledge & Memory
2

Related MCP Servers

Clanki
Education & Learning Tools App Automation
jasperket
A
license
A
quality
B
maintenance
An MCP server that enables AI assistants like Claude to interact with Anki flashcard decks, allowing users to create, manage, and update flashcards through natural language conversations.
Updated 20 days ago (2026-09-17 01:38 UTC)
9
44
MIT
Anki MCP Server
Education & Learning Tools Note Taking
ankimcp
A
license
Not graded
quality
A
maintenance
An MCP server that enables AI assistants to interact with the Anki flashcard application for studying, deck management, and note creation. It supports natural language interaction for reviewing cards, searching content, and managing media files across local and remote environments.
Updated 19 days ago (2026-09-18 15:17 UTC)
1,773 npm
502
MIT
TalkToAnki
Education & Learning Tools Note Taking App Automation
muxuuu
A
license
Not graded
quality
D
maintenance
An MCP server that enables AI assistants to seamlessly manage Anki flashcards, decks, and templates through the AnkiConnect API. It supports intelligent querying, batch note creation, and detailed study progress analysis using natural language.
Updated a year ago (2025-06-22 09:57 UTC)
4
MIT
Anki MCP Server
Education & Learning Tools Knowledge & Memory
matteo1222
A
license
B
quality
D
maintenance
A Model Context Protocol (MCP) server that integrates with Anki flashcard application, allowing LLM applications like Claude to interact with your Anki decks and cards.
Updated a year ago (2025-08-01 03:17 UTC)
11
334 npm
1
MIT