Skip to main content
Glama
slide-anki-mcp
by 2Mesh
README.md
# slide-anki-mcp

[![tests](https://github.com/2Mesh/slide-anki-mcp/actions/workflows/test.yml/badge.svg)](https://github.com/2Mesh/slide-anki-mcp/actions/workflows/test.yml)

An MCP server for students who study from lecture slides. It makes Claude (or any MCP client) quote the slide for every Anki card, and it rejects a card when the quote is not really on that slide.

Study tools often write cards from the model's own knowledge. If your exam is graded against your lecturer's slides, that is a risk. Here every card carries a quote from the slide, the server checks the quote letter by letter, and the quote is written into the card so you can read it next to the answer.

**What it proves:** the quote is on the slide, and the answer is inside the quote.
**What it does not prove:** that the card is correct. You still need to read your cards.

## Quick start

```bash
pip install git+https://github.com/2Mesh/slide-anki-mcp
claude mcp add slide-anki -- slide-anki-mcp
```

Then ask Claude: "Read C:\lectures\renal.pdf with slide-anki. Make cards from slides 3 to 10, quote each slide in the evidence field, and export to C:\lectures\renal.tsv." Give the full path to the PDF. Import the `.tsv` in Anki with File → Import.

Needs Python 3.10 or newer. It is not on PyPI yet, so install from GitHub as above.

## Tools

| Tool | What it does |
|---|---|
| `list_slides(pdf_path)` | Slide numbers with first line and length. Warns about slides with little or no text |
| `get_slide(pdf_path, slide)` | Exact text of one slide, to copy quotes from |
| `check_cards(pdf_path, cards)` | Checks each card. A failing card comes back with the slide text so the quote can be fixed |
| `export_anki(pdf_path, cards, out_path)` | Writes a new `.tsv` only if every card passes. Each card is tagged `Slide_N`. Exact duplicates are written once |

A card is:

```json
{"front": "Where is ADH produced?", "back": "the hypothalamus",
 "evidence": "ADH is produced in the hypothalamus", "slide": 1}
```

A card passes only if all of these are true:

1. The slide has text. A slide with none is rejected with "slide has no text, cannot verify".
2. `evidence` is at least 4 words and is on the cited slide exactly as quoted. Case, extra spaces, a word split by a hyphen at a line break, and dash or quote style are ignored. Everything else must match, including `<`, `>`, `+`, `-` and numbers. Superscripts are kept: `10⁵` is not `105`.
3. `back` is inside `evidence`, and is not cut from a longer token: `1500 ml` is not found in `1000-1500 ml`, and `70 mV` is not found in `-70 mV`.

`export_anki` also refuses an `out_path` that does not end with `.tsv`, that already exists, or whose folder does not exist. It never overwrites a file.

## Example

Made with a small two-slide test PDF. Slide 1 says "ADH is produced in the hypothalamus", slide 2 says "Normal plasma sodium is 135-145 mmol/L". `check_cards` with one wrong card and one right card:

```json
[
  {"slide": 1, "ok": false, "unsupported": ["evidence is not on this slide exactly as quoted"]},
  {"slide": 2, "ok": true, "unsupported": []}
]
```

(The failing card also comes back with `slide_text`, left out here.) After fixing the first card and sending the sodium card twice by mistake, `export_anki` returns:

```json
{"written": "/path/to/cards.tsv", "count": 2, "duplicates_skipped": [2]}
```

and the file contains:

```
#separator:tab
#html:false
#tags column:3
"Where is ADH produced?"	"the hypothalamus  |  Source (slide 1): ADH is produced in the hypothalamus"	"slides Slide_1"
"Normal plasma sodium?"	"135-145 mmol/L  |  Source (slide 2): Normal plasma sodium is 135-145 mmol/L"	"slides Slide_2"
```

The header lines are read by Anki 2.1.54 and newer. Older versions need the field separator set to Tab by hand. Every field is quoted so a front that starts with `#` is not read as a header line. I have not tried the import in Anki yet.

## Install for Claude Desktop

Open `claude_desktop_config.json` (Windows: `%APPDATA%\Claude\claude_desktop_config.json`, macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`), add the server, then restart Claude Desktop:

```json
{
  "mcpServers": {
    "slide-anki": {
      "command": "slide-anki-mcp"
    }
  }
}
```

If Claude cannot find the command, put its full path in `"command"`. Get the path with `where slide-anki-mcp` on Windows or `which slide-anki-mcp` on macOS and Linux. If you installed inside a virtual environment, you need that full path for Claude Code as well.

## What it cannot catch

- **Meaning.** It checks that words are on the slide, not what they mean. If the slide says "Mitral valve does not have three cusps", a card with the back "three cusps" and that full sentence as evidence passes. The "does not" is in the exported card, so you can see it, but the server does not detect it.
- **The front.** The question is never checked. A true sentence under the wrong question passes.
- **Units that differ only in case.** Case is ignored, so `mM` and `mm`, or `Mg` and `mg`, count as the same.
- **Quotes that start right after a dash or sign.** If a slide line reads `Beverages -1000-1500 ml`, the quote has to include the dash. A quote that cuts a number, unit or range in the middle (`135` from `135-145 mmol/L`, `140 mmol` from `140 mmol/L`) is rejected.
- **Paraphrases.** A correct answer in other words is rejected. Copy the slide's wording. Small differences such as "200mL" on the slide and "200 mL" in the card are also rejected.
- **Images.** Text inside pictures, scanned pages and diagrams is not read, and cards that cite those slides are rejected. On one real 40-slide lecture, 4 slides had no text at all and 7 more had under 40 characters, mostly section titles.
- **Bad text extraction.** If the PDF stores text in an odd way, the extracted words can be split or out of order, and correct cards will fail.

For the numbers: an earlier version of this tool matched the answer against the slide with symbols removed. On a real 40-slide lecture it accepted 8 of 30 cards that were made wrong on purpose, for example a changed number or a dropped "No". This version keeps symbols and requires a quote. On a new set of 30 correct and 29 wrong cards from the same lecture (written by a reviewer, so a small and friendly sample), it accepted 26 of the 30 correct cards and 0 of the 29 wrong ones. The 4 rejected correct cards were quotes shorter than 4 words, a quote with `and` where the slide has `&`, and a quote that left out a leading dash. The wrong cards did not include a dropped "not", because that lecture has no usable place for one, so that case is untested on real slides.

### Arabic

Arabic works on a generated test PDF (Arial or DejaVu font, letters shaped and stored in right-to-left display order with `arabic-reshaper` and `python-bidi`): exact Arabic quotes pass, wrong ones fail, and short vowel marks are ignored. It is not tested on a real Arabic lecture. If a PDF stores Arabic in another order, the extracted text comes out reversed and Arabic cards will not match.

## Roadmap

These are real gaps, not promises:

- **OCR for image slides**, so text in pictures and scanned decks can be checked.
- **Meaning-aware checking**, so a correct paraphrase can pass and a phrase taken out of context can be caught.
- **Testing on real Arabic lectures and a real Anki import.**

## Develop

```bash
pip install -e ".[test]"
pytest
python tests/e2e_stdio.py
```

See [CONTRIBUTING.md](CONTRIBUTING.md).

MIT licensed.

TDQS

A4/5.0

Scored across 4 tools

Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count5/5

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.

Completeness4/5

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.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues