Anki MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| anki_add_noteC | Add a flashcard to an Anki deck |
| anki_add_notesC | Add multiple flashcards to an Anki deck |
| anki_create_deckC | Create a new Anki deck |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The tools have overlapping purposes, as 'anki_add_note' and 'anki_add_notes' both handle adding flashcards, differing only in single vs. multiple notes. This could cause misselection if an agent needs to add one note but picks the plural version, or vice versa. However, the descriptions clarify the distinction, preventing complete confusion.
All tool names follow a consistent 'anki_verb_noun' pattern with snake_case, making them predictable and easy to parse. The verbs ('add', 'create') are clear and appropriately matched to their actions, ensuring no deviation in naming conventions across the set.
With only 3 tools, the server feels under-scoped for managing Anki flashcards, as it lacks essential operations like retrieving, updating, or deleting notes or decks. This minimal set may force agents into dead ends when trying to perform common tasks beyond basic creation.
The tool surface is severely incomplete for Anki management, missing critical CRUD operations such as getting or listing notes/decks, updating existing content, or deleting items. This creates significant gaps that will likely cause agent failures in typical workflows, as users cannot interact with existing data.