slide-anki-mcp
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_slidesA | List every slide in a lecture PDF (full path) with its first line and text length. A slide with a 'warning' has little or no text. Cards cannot be checked against it. |
| get_slideA | Return the exact text of one slide (1-based). Copy evidence quotes from this text. |
| check_cardsA | Check each card {front, back, slide, evidence} against the text of its slide. 'evidence' must be a quote of at least 4 words copied exactly from the cited slide, and 'back' must be inside that quote. Symbols, signs and numbers must match exactly. A passing card means the quote is on the slide. It does not mean the card is correct: read the evidence next to the answer. A failing card comes back with the slide text so the quote can be fixed. |
| export_ankiA | Write cards to a new Anki-importable .tsv, only if every card passes check_cards. out_path must end with .tsv, be in an existing folder, and must not exist yet. The evidence quote and slide number are written at the end of each answer. Exact duplicates (same front and back) are written once; the indexes of the skipped copies are listed in 'duplicates_skipped'. |
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 role in a linear pipeline: list_slides gives an overview, get_slide retrieves full text, check_cards validates cards against a slide, and export_anki writes the final file. There is no meaningful overlap or risk of misselection between them.
All four tools follow the same predictable snake_case verb_noun pattern (list_slides, get_slide, check_cards, export_anki). The naming is fully consistent and self-explanatory.
Four tools is a minimal, well-scoped set for the slide-to-Anki workflow. Each tool is necessary for a distinct step and none feels redundant or missing.
The tool surface covers the core lifecycle: discover slides, read text, validate cards, and export passing cards. Minor gaps exist, such as no batch slide retrieval or a way to inspect/update exported files, but agents can work around these by calling get_slide repeatedly.