mcpField
H
hearthstone-oracle

hearthstone-oracle

Local
github.com/gregarioGames & Entertainment2Updated 26w ago

About hearthstone-oracle

hearthstone-oracle is an MCP server for Hearthstone card search, deck analysis, and strategy coaching. It combines a locally stored card database with built-in strategy knowledge.

Key features

  1. 01Search and look up cards
  2. 02Decode deck codes
  3. 03Analyze deck curves and archetypes
  4. 04Browse strategy and class identities
  5. 05Explain matchups and game concepts

Use cases

  1. 01Find cards by text, class, cost, or keyword
  2. 02Review a deck's list and mana curve
  3. 03Assess a deck's gameplan and matchups
  4. 04Get explanations of Hearthstone concepts

MCP support

The MCP server provides nine tools for card search and lookup, deck decoding and analysis, archetype and class information, matchup dynamics, and concept explanations.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"gregario-hearthstone-oracle": {
"command": "npx",
"args": [
"-y",
"hearthstone-oracle"
]
}
}
}
Run commandnpx -y hearthstone-oracle

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmhearthstone-oracle0.1.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

npm version npm downloads Node.js 18+ MCP Compatible MIT License Sponsor hearthstone-oracle MCP server

hearthstone-oracle

Hearthstone MCP server with card search, deck analysis, and strategy coaching. Gives LLMs access to every Hearthstone card plus built-in strategy knowledge for deck building and gameplay advice.

Features

  • Complete card database from HearthstoneJSON — every collectible card, auto-updated
  • Deck decoding and analysis — paste a deck code, get full card list, mana curve, and archetype breakdown
  • Strategy knowledge — archetypes, class identities, matchup dynamics, and game concepts
  • 9 MCP tools — search, lookup, decode, analyze, coach

Quick Start

claude mcp add hearthstone-oracle -- npx -y hearthstone-oracle

Card data is downloaded automatically from HearthstoneJSON on first run and stored locally in ~/.hearthstone-oracle/. No API key required.

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "hearthstone-oracle": {
      "command": "npx",
      "args": ["-y", "hearthstone-oracle"]
    }
  }
}

Tools

ToolDescription
search_cardsSearch cards by name, text, class, cost, type, rarity, set, or keyword
get_cardGet complete details for a specific card with fuzzy matching
get_keywordLook up keyword/mechanic definitions with related cards
decode_deckDecode a deck code into full card list with mana curve
analyze_deckAnalyze a deck's archetype, gameplan, strengths, and matchup profile
get_archetypeLearn about deck archetypes (aggro, control, combo, midrange, tempo, value)
get_class_identityStrategic identity of each Hearthstone class
get_matchupTheoretical matchup dynamics between archetypes
explain_conceptFundamental game concepts explained for Hearthstone

How It Works

Two-layer architecture:

  1. Card data layer — Full card database from HearthstoneJSON, stored in a local SQLite database with FTS5 full-text search. Cards are fetched on first run and updated when newer game builds are available.
  2. Strategy layer — Built-in strategy knowledge covering archetypes, class identities, matchup theory, and core game concepts. Enables the server to provide coaching and analysis, not just raw card data.

Data Source

Card data provided by HearthstoneJSON by HearthSim. Auto-extracted from game files. Unrestricted use.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.