Skip to main content
Glama
enesjakozh
captain-blue210

Anki MCP Server

by captain-blue210
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Servidor MCP de Anki

Un servidor MCP (Protocolo de contexto de modelo) para Claude Desktop que se conecta a Anki a través de AnkiConnect y recupera tarjetas etiquetadas con leech.

Características

  • Se conecta a Anki a través de la API AnkiConnect

  • Recupera tarjetas con etiquetas "leech"

  • Agrega etiquetas de revisión con fecha estampada a las tarjetas

  • Proporciona datos completos de tarjetas para que Claude los analice.

  • Se puede utilizar con Claude Desktop

Related MCP server: Anki MCP

Prerrequisitos

  • Anki instalado y funcionando

  • Complemento AnkiConnect instalado en Anki

  • Node.js y npm

Instalación

  1. Clonar este repositorio:

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

  2. Instalar dependencias:

    npm install

  3. Construir el proyecto:

    npm run build

Configuración

El servidor se puede configurar mediante variables de entorno. Copie el archivo de ejemplo proporcionado para crear su propia configuración:

cp .env.example .env

Luego edite el archivo .env para personalizar su configuración:

Variable de entorno

Descripción

Valor predeterminado

ANKI_CONNECT_URL

La URL de la API de Anki Connect

http://localhost:8765

ANKI_CONNECT_VERSION

La versión de la API de Anki Connect a utilizar

6

ANKI_MOCK_MODE

Habilitar el modo simulado para realizar pruebas (verdadero/falso)

false

Si no se configuran las variables de entorno, el servidor utilizará los valores predeterminados.

Cómo encontrar su dirección IP local para AnkiConnect

Si no puede conectarse al localhost , deberá usar la dirección IP local de su computadora. Configure su archivo .env con:

ANKI_CONNECT_URL=http://YOUR_LOCAL_IP:8765

Para encontrar su dirección IP local:

  • macOS : Abra la Terminal y ejecute ifconfig o ipconfig getifaddr en0 (para WiFi)

  • Windows : Abra el símbolo del sistema y ejecute ipconfig

  • Linux : Abra la terminal y ejecute ip addr show o hostname -I

Busque direcciones IPv4 como 192.168.xx o 10.xxx en la salida.

Configuración de prueba

Para realizar pruebas, se proporciona un archivo de configuración separado .env.test :

cp .env.example .env.test

Edite .env.test para establecer valores específicos de la prueba:

ANKI_CONNECT_URL=http://localhost:8765
ANKI_CONNECT_VERSION=6
ANKI_MOCK_MODE=true

Para ejecutar en modo de prueba:

npm run start:test

Uso

  1. Asegúrese de que Anki se esté ejecutando con AnkiConnect instalado

  2. Ejecute el servidor MCP:

    npm start

Configuración de Claude Desktop

Para utilizar este servidor MCP con Claude Desktop:

  1. Abra Claude Desktop

  2. Edite el archivo de configuración de Claude Desktop ubicado en:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

    • Ventanas: %APPDATA%\Claude\claude_desktop_config.json

    • Linux: ~/.config/Claude/claude_desktop_config.json

  3. Agregue la siguiente configuración a la sección mcpServers :

{
  "mcpServers": {
    "anki": {
      "command": "node",
      "args": ["path/to/anki-mcp-server/dist/index.js"]
    }
  }
}

Reemplace "path/to/anki-mcp-server" con la ruta real a donde clonó este repositorio.

Uso de la herramienta MCP

Una vez configurado, podrás utilizar las siguientes herramientas en Claude:

Ejemplo de uso

Could you analyze my Anki leech cards and suggest ways to improve my study?

Claude utilizará el servidor MCP para recuperar tus tarjetas sanguijuelas y analizarlas.

Herramientas disponibles

obtener_tarjetas_sanguijuela

Recupera tarjetas etiquetadas como sanguijuelas de Anki.

Parámetros:

  • detailed (opcional, booleano, predeterminado: verdadero): si se deben devolver datos completos de la tarjeta o solo identificaciones

  • count (opcional, número): Número de cartas aleatorias a devolver (predeterminado: todas las cartas)

tarjetas revisadas por etiqueta

Añade una etiqueta de "revisado" con fecha a tarjetas específicas. Esto te permite rastrear qué tarjetas has revisado con Claude.

Parámetros:

  • card_ids (obligatorio, matriz de números): Matriz de identificaciones de tarjetas para etiquetar como revisadas

  • custom_tag_prefix (opcional, cadena, predeterminado: "見直し"): prefijo personalizado para la etiqueta

La etiqueta tendrá el formato見直し_YYYYMMDD (o su prefijo personalizado si se especifica).

Ejemplo de uso en Claude:

I've reviewed these cards, please tag them as reviewed: [1234567890, 1234567891]

Solución de problemas

  • "No se pudo conectar a Anki" : asegúrese de que Anki se esté ejecutando y que AnkiConnect esté instalado correctamente.

  • "No se encontraron tarjetas sanguijuelas" : No tienes ninguna tarjeta etiquetada como "sanguijuela" en Anki.

  • Problemas de conexión con localhost : si no puede conectarse usando localhost :

    1. Encuentre su dirección IP local como se describe en la sección Configuración

    2. Actualice su archivo .env para usar ANKI_CONNECT_URL=http://YOUR_LOCAL_IP:8765

    3. Asegúrese de que AnkiConnect esté configurado para permitir conexiones desde su dirección IP

    4. Reinicie el servidor MCP después de realizar estos cambios

  • La etiqueta no aparece : asegúrese de proporcionar identificaciones de tarjetas válidas a la herramienta tag_reviewed_cards

Modo de prueba

Para realizar pruebas sin afectar los datos reales de Anki, puedes usar el modo simulado:

  1. Establezca ANKI_MOCK_MODE=true en su archivo .env o utilice el archivo .env.test proporcionado

  2. Ejecute el servidor con npm run start:test

En el modo simulado, el servidor simulará todas las operaciones de Anki sin conectarse a él. Esto resulta útil para probar las integraciones de Claude sin arriesgarse a modificar los datos.

Desarrollo

Para ejecutar el servidor en modo de desarrollo con recarga en caliente:

npm run dev

Para el desarrollo con el modo simulado habilitado:

npm run dev:test

Licencia

Instituto Tecnológico de Massachusetts (MIT)

Available Tools

2 tools
get_leech_cardsB

Retrieve cards tagged as leeches from Anki

ParametersJSON Schema
NameRequiredDescriptionDefault
detailedNoWhether to return detailed card information or just IDs
countNoNumber of random cards to return (defaults to all)

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are provided, so the description carries full burden for behavioral disclosure. While 'Retrieve' implies a read operation, it doesn't specify whether this requires authentication, how results are returned (format, pagination), error conditions, or performance characteristics. The description is minimal and lacks behavioral context.

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

Conciseness5/5

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

The description is a single, clear sentence with zero wasted words. It's appropriately sized for a simple retrieval tool and front-loads the essential information. Every word earns its place.

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

Completeness3/5

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

For a retrieval tool with 2 parameters and 100% schema coverage but no annotations or output schema, the description provides basic purpose but lacks behavioral context and usage guidance. It's minimally adequate but has clear gaps in explaining how the tool behaves and when to use it.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description adds no parameter-specific information beyond what's in the schema. Baseline 3 is appropriate when the schema does the heavy lifting, though no additional semantic context is provided.

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

Purpose4/5

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

The description clearly states the action ('Retrieve') and target resource ('cards tagged as leeches from Anki'), making the purpose immediately understandable. It doesn't explicitly differentiate from its sibling tool 'tag_reviewed_cards', but the distinction is implied through the different operations (retrieval vs tagging).

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives or in what context. The description only states what the tool does, without mentioning prerequisites, timing considerations, or relationship to the sibling tool beyond their different names.

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

tag_reviewed_cardsC

Add a 'reviewed on date' tag to specified cards

ParametersJSON Schema
NameRequiredDescriptionDefault
card_idsYesArray of card IDs to tag as reviewed
custom_tag_prefixNoCustom prefix for the tag (default: '見直し')

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It implies a mutation ('Add'), but doesn't clarify if this is destructive (e.g., overwrites existing tags), requires authentication, has side effects, or includes error handling. The description is minimal and lacks critical behavioral details for a write operation.

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

Conciseness5/5

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

The description is a single, efficient sentence with zero waste. It's front-loaded with the core action and resource, making it easy to parse quickly.

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

Completeness2/5

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

Given the tool's mutation nature (adding tags), no annotations, and no output schema, the description is incomplete. It doesn't cover behavioral aspects like permissions, side effects, or return values, leaving significant gaps for an AI agent to understand how to use it correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema fully documents both parameters (card_ids and custom_tag_prefix). The description adds no additional parameter semantics beyond implying the tag format ('reviewed on date'), which is already suggested by the schema's default value for custom_tag_prefix. Baseline 3 is appropriate as the schema does the heavy lifting.

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

Purpose4/5

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

The description clearly states the action ('Add') and target resource ('tag to specified cards'), with the specific tag content 'reviewed on date' mentioned. However, it doesn't differentiate from the sibling tool 'get_leech_cards' (which presumably retrieves rather than modifies cards), so it doesn't fully distinguish from alternatives.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention the sibling tool 'get_leech_cards' or any other context for selection, nor does it specify prerequisites like required permissions or system states.

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.

  1. 2 tool updates
    • First observedget_leech_cards
    • First observedtag_reviewed_cards
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

B3.1/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have completely distinct purposes: one retrieves cards with a specific tag, while the other adds a tag to cards. There is no overlap in functionality or ambiguity between them.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern (get_leech_cards, tag_reviewed_cards) with clear actions and objects, making them predictable and easy to understand.

Tool Count2/5

With only 2 tools, the server feels thin for an Anki integration, lacking basic operations like creating cards, reviewing cards, or managing decks. This minimal set limits agent workflows significantly.

Completeness2/5

The toolset is severely incomplete for an Anki server, missing core CRUD operations for cards, decks, and reviews. Agents cannot perform essential tasks like adding new cards or scheduling reviews, leading to dead ends.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches