Skip to main content
Glama
Harshal12355

MTG Deckbuilder MCP

by Harshal12355

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
search_cardsB

Search cards with full Scryfall syntax (https://scryfall.com/docs/syntax).

Examples: t:legendary t:creature id:bg, o:"draw a card" id<=u cmc<=2 f:commander, otag:ramp id<=g usd<1, is:commander keyword:partner. order="edhrec" sorts by popularity in Commander. detail="full" includes oracle text.

get_cardB

Look up one card by name (fuzzy by default, so misspellings and partial names work).

Returns oracle text, types, colours, legalities, price and the card's heuristic deck roles.

get_card_rulingsC

Official rulings and Gatherer notes for a card, plus its oracle text for context.

get_card_printingsB

Every printing of a card, cheapest first, with set and USD prices. Useful for budget builds.

autocomplete_card_nameA

Suggest up to 20 real card names for a partial or misspelled name.

random_cardB

A random card, optionally restricted by a Scryfall query (e.g. is:commander id:ur).

analyze_deckB

Analyse a pasted decklist (Moxfield, Arena, Archidekt, MTGO or plain 1 Card Name lines).

Reports legality for the format (size, copies, colour identity, bans), mana curve, colour pips vs land sources, card roles (ramp, draw, removal, wipes, tutors...), gaps against a typical Commander template, Game Changers, and total price. Pass commanders if the list doesn't mark them. budget_per_card flags cards above that USD price.

find_combosB

Find combos already in a deck and combos that are one card away (Commander Spellbook).

Also lists combos that would work with a different commander or by adding colours.

search_combosB

Search Commander Spellbook combos, most popular first.

Query syntax examples: card:"Thassa's Oracle", result:"infinite mana" id<=bg, cards=2 result:"win the game".

edhrec_recommendationsA

EDHREC recommendations for a commander: high-synergy cards, top cards, and per-type lists.

  • theme: an EDHREC theme like "tokens", "+1/+1 counters", "aristocrats" (see themes in the result).

  • budget: "budget" or "expensive" EDHREC variants.

  • decklist: if given, cards already in the deck are removed so results are suggested adds.

  • categories: restrict to list tags such as ["highsynergycards", "topcards", "creatures", "instants"]. Each card shows inclusion % (share of this commander's decks running it) and synergy % (how much more often it appears here than in other decks of these colours).

edhrec_cardB

EDHREC data for a card: the commanders that play it most and cards commonly played with it.

price_decklistB

Quick price check of a decklist: per-card USD price and total, most expensive first.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.5/5.0

Scored across 12 tools

Disambiguation4/5

Most tools have clearly distinct purposes (card lookup vs. search vs. autocomplete vs. printings vs. rulings). The main overlap is find_combos vs. search_combos and price_decklist vs. analyze_deck's price output, but descriptions clarify deck-scoped detection versus general combo search and a quick price check versus full analysis.

Naming Consistency4/5

Almost all tools are snake_case with a verb_noun feel (find_combos, search_cards, get_card, analyze_deck). A few are noun-first (random_card, edhrec_card, price_decklist), which is a minor deviation but still readable and predictable.

Tool Count5/5

12 tools is well within the sweet spot and each earns its place, covering card data, combos, EDHREC recommendations, and deck analysis without redundancy.

Completeness4/5

The surface covers card discovery, lookups, rulings, printings, combo detection, EDHREC synergy, and deck pricing/analysis thoroughly. Minor gaps like no explicit deck export/save or mana-base suggestion tool exist, but these are largely out of the stated analysis/recommendation scope.

Maintenance

ActivityMaintained
ResponsivenessNo issues