mtga-mcp

A local MCP server for querying your Magic: The Gathering Arena collection in natural language. It ingests MTGA's own card catalog, your owned cards from the game log, and Scryfall card data into a local SQLite database, then exposes query tools that any MCP client (Claude Desktop, Claude Code) can call.

Nothing leaves your machine except the one-time Scryfall bulk-data download. There is no model bundled here — your MCP client supplies the LLM.

How it works

The join key is MTGA's GrpId, which equals Scryfall's arena_id. Everything lands in ~/.local/share/mtga-mcp/mtga.db (override with MTGA_MCP_DATA_DIR).

Paths are macOS-specific (this project targets a native macOS MTGA install launched via Heroic). Adjust src/mtga_mcp/paths.py for other platforms.

Related MCP server: iwantmymtg-mcp

Setup

uv sync

Step 0 — enable MTGA Detailed Logs (required for owned counts)

MTGA only writes your collection to Player.log when detailed logging is on:

1. In MTGA: Settings → Account → check "Detailed Logs (Plugin Support)".

2. Restart MTGA and open your Collection screen once.

The card catalog and Scryfall data work without this; only owned quantities need it.

Import data

uv run mtga-mcp import            # runs all three steps
# or selectively:
uv run mtga-mcp import --catalog      # ~19.7k cards from MTGA
uv run mtga-mcp import --collection   # your owned cards + wildcards
uv run mtga-mcp import --scryfall     # enrich (downloads a ~77MB bulk file, cached)

Re-run import --collection whenever your collection changes; re-run --scryfall occasionally for new sets/prices (it only re-downloads when Scryfall has newer data).

Use it from an MCP client

Claude Code

claude mcp add mtga -- uv --directory /Users/scott/git/mtga-mcp run mtga-mcp serve

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mtga": {
      "command": "uv",
      "args": ["--directory", "/Users/scott/git/mtga-mcp", "run", "mtga-mcp", "serve"]
    }
  }
}

Then ask things like:

• "How complete is my collection? Show the per-rarity breakdown and my wildcards."

• "Which rares am I missing from FDN?"

• "List blue instants I own that are Standard-legal."

Tools exposed

Database tables: cards, collection(grp_id, count), wildcards(kind, count), meta, decks, deck_cards.

Deck buildability

Import meta decks (or your own brews), then ask what you're missing and what to build.

# Import from pasted Arena/MTGO text (tag it with meta info for ranking):
pbpaste | uv run mtga-mcp deck import --paste --name "Mono-Red" --format Standard \
  --best-of 1 --meta-share 0.18
uv run mtga-mcp deck import --file list.txt --name "Dimir Midrange" --best-of 3 --tier 1

# Import from a deck host with a public API:
uv run mtga-mcp deck import --url https://archidekt.com/decks/1234567
uv run mtga-mcp deck import --url https://www.moxfield.com/decks/AbCdEf

uv run mtga-mcp deck gap "Mono-Red"          # cards + wildcards you still need
uv run mtga-mcp deck best --best-of 1         # best deck you can build right now
uv run mtga-mcp deck craft-priority           # what to craft to unlock the most decks

The north-star query — "given my cards and the current meta, what's the best Bo1/Bo3 deck I could build?" — is deck best, which ranks decks by meta strength × how few wildcards you're missing. Strength comes from the --tier / --meta-share / --win-rate you supply at import (meta sites don't expose this programmatically); with none supplied it ranks purely by buildability.

A note on meta-deck sources

The big meta sites (MTGGoldfish, Untapped, AetherHub, mtgdecks) actively block automated access — Cloudflare, robots ai-train=no, blocked bot user-agents, and blocked export endpoints. So this tool imports decklists from pasted text and deck-host public APIs (Archidekt, Moxfield) instead. A best-effort MTGGoldfish scraper exists behind an explicit --allow-scrape flag but is brittle and may fail; pasting the Arena export (one click in your browser) is the reliable path.

Development

uv run pytest

Not yet implemented (ideas)

Auto-refreshing meta snapshots, live log-watching, format-legality enforcement, deck similarity/clustering, non-English card names.