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 |
|---|---|
| get-collection-overviewB | Get comprehensive information about the Anki collection including decks, models, and fields |
| get-cards-reviewedB | Get the number of cards reviewed by day |
| find-notesC | Find notes matching a query in Anki |
| add-or-update-notesC | Add new notes or update existing ones in Anki |
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 4 tools
Each tool has a clearly distinct purpose: add-or-update-notes handles note creation/modification, find-notes handles search queries, get-cards-reviewed provides review statistics, and get-collection-overview gives collection metadata. There is no overlap or ambiguity between these functions.
The tools follow a consistent verb-object naming pattern (e.g., add-or-update-notes, find-notes) with clear actions and targets. The only minor deviation is the hyphenated style, which is consistent across all tools but differs from more common snake_case or camelCase conventions.
With 4 tools, this server is well-scoped for managing an Anki collection. It covers core operations like note management, search, review tracking, and collection overview without being overly sparse or bloated.
The toolset covers essential Anki operations: CRUD for notes (add/update and find), review analytics, and collection metadata. A minor gap is the lack of explicit delete or deck management tools, but agents can likely work around this using existing tools.