Context7
Up-to-date docs for AI agents
作者による説明(英語の原文)
MCP server for Disney Lorcana TCG: enrich collections, search cards, build decks, audit data.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"lorcana": {
"command": "uvx",
"args": [
"lorcana-mcp"
]
}
}
}ターミナルでこれを実行します
claude mcp add lorcana -- uvx lorcana-mcpプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"lorcana": {
"command": "uvx",
"args": [
"lorcana-mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"lorcana": {
"type": "stdio",
"command": "uvx",
"args": [
"lorcana-mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント IcaroBichir で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(2.6.1)がレジストリに届いたのは20 日前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにPython (uv)も必要です。
同じカテゴリには:Context7, Codebase Memory, Exa
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
MCP server that connects Claude to Disney Lorcana card data. Export your collection from TCGPlayer, hand it to Claude, and get it fully enriched with ink cost, stats, keywords, abilities, and format legality — plus a ready-to-import file for dreamborn.ink.
What it does: plug this into Claude and it becomes a Disney Lorcana expert that knows your actual collection — no more tab-switching between TCGPlayer, dreamborn.ink, and a wiki.
Once it's connected, you can just talk to Claude like:
Everything reads from public card APIs plus your own exported CSV — no account, no login, nothing to configure.
Claude Desktop — one click: download lorcana-mcp.mcpb and double-click it (or Settings → Extensions → Install extension…). No terminal, no Python install, nothing to configure.
Everything else — one command:
1. Connect it (uvx fetches it on demand — install uv first, or pip install lorcana-mcp and drop the uvx):
claude mcp add lorcana -- uvx lorcana-mcp serve
Using Claude Desktop config, Cursor, VS Code, Windsurf, Cline, or Zed instead? Every client is covered in [docs/INSTALL.md](docs/INSTALL.md).
2. Talk to it: Export your collection from TCGPlayer (My Account → My Collection → Export), then just say:
"Enrich my collection at /path/to/your/export.csv"
That's it — Claude does the rest. Everything below is reference detail for when you want more control.
Thirteen tools are available in Claude once the server is running:
| Tool | What it does |
|---|---|
enrich_csv | Enriches a raw TCGPlayer export with Ink, Cost, Type, Subtypes, STR/WIL/Lore, Inkable, Keywords, and Abilities. Writes an enriched CSV and a dreamborn.ink-ready import file next to the input. refresh_prices=True also refreshes TCG Market Price with a live tcgcsv.com lookup. |
lookup_card | Looks up any card by name. Returns full stats, ability text, format legality, and card image URL. |
resolve_card | Fuzzy-resolves an informal, misspelled, or subtitle-less card name (e.g. "goofy musketeer", "elsa"). Returns a single confident match, a ranked top-3 to disambiguate, or nothing found. |
list_printings | Lists every printing of a card — or every card sharing a character name — side by side: set, number(s), cost, stats, rarity, per-format legality, and cheapest market price. Optional fmt adds a ✓/✗ legality column. For "which printing of X is Core-legal / cheapest?". |
search_cards | Searches the full card pool by color, type, rarity, set, cost range, keyword, ability text, or subtype — with pagination. |
find_song_synergies | Finds every character that can sing a given song (or a raw cost threshold), split into Singer-keyword discount picks and plain cost-qualifiers. Optionally flags which ones you own. |
filter_collection | Filters your collection to cards legal in a given format: core, infinity, core_zh, core_ja, or poorcana. |
audit_csv | Compares an enriched collection against live API data and reports any stale or wrong fields. |
analyze_deck | Analyzes a raw deck list (4x Card Name per line) for ink curve, inkable split, color split, card types, estimated lore/turn, and Core Constructed legality (60-card min, max 4 copies, ≤2 ink colors). |
what_am_i_missing | Compares a deck list against your collection: what you already own, what's missing or short, and a live TCGPlayer cost estimate (via tcgcsv.com) to complete it. |
build_deck | Automatically assembles a legal, curve-balanced ~60-card decklist for an ink pair/format, in one of 3 modes: collection (only cards you own), ideal (best deck regardless of ownership, priced to complete if you pass a collection CSV), or market (best deck, fully priced, ignoring ownership). Also builds for format="coconut" — Ravensburger's multiplayer singleton beta (up to 3 ink colors, 1 copy of everything except your chosen Coconut's associated character at up to 4). Pass theme (a classification like "princess"/"detective", or a character name) to build a tribal deck — inks are auto-picked if you omit them — and include_preview=True to use cards from an announced set before it's legal. A heuristic curve/keyword-value builder, not a synergy/combo detector. |
build_sealed_deck | Builds the best 40-card Sealed / prerelease deck from an opened card pool (6 packs, ~72 cards). Takes one card per line — names (informal/misspelled is fine) or the collector numbers printed on the cards (123, 123/204), so a photo of the pool can be transcribed by your MCP client and passed straight in. Sealed rules: 40-card minimum, no ink limit, no copy limit. Ranks every ink pair by pool depth, builds around the deepest one, splashes extra inks only when needed to reach 40, and lists the best sideboard cards plus any ambiguous/unrecognized lines (never guessed). |
get_meta | Returns a hand-maintained Core Constructed metagame snapshot: every two-ink pair's tier, rough meta share, and playstyle, plus recent tournament results — optionally filtered to one pair (ink_colors="Emerald,Steel"). With event= ("nac", "asia", "kobe", …) returns that tournament's full standings and decklists instead. Not a live fetch — there's no free structured feed for this the way there is for card data — so it's a versioned snapshot bundled at release time, and says so explicitly in its own output. |
| Directory | Link |
|---|---|
| MCP Registry (official) | registry.modelcontextprotocol.io |
| mcp.so | mcp.so/server/lorcana-mcp |
| PyPI | pypi.org/project/lorcana-mcp |
You don't have to install anything if you use uvx (below) or the Claude Desktop bundle. To install the package explicitly:
pip install lorcana-mcp
From source:
git clone https://github.com/IcaroBichir/lorcana-mcp
cd lorcana-mcp pip install .
Claude Desktop bundle: lorcana-mcp.mcpb on the releases page — a one-click install that bundles its own runtime. Built from packaging/mcpb/.
lorcana-mcp is a local stdio server — it runs on your machine, no hosting or API key. [docs/INSTALL.md](docs/INSTALL.md) is the full guide, with copy-paste config for every client. The short version:
| Client | Supported | How |
|---|---|---|
| Claude Desktop | ✅ | One-click .mcpb bundle, or config below |
| Claude Code | ✅ | claude mcp add lorcana -- uvx lorcana-mcp serve |
| Cursor · VS Code · Windsurf · Cline · Zed | ✅ | stdio config — see docs/INSTALL.md |
| Any other stdio MCP client | ✅ | Command: uvx lorcana-mcp serve (or lorcana-mcp serve if pip-installed) |
| Claude.ai (web) · ChatGPT | ❌ | Those need a hosted remote server; this one is local-only — see docs/INSTALL.md |
claude mcp add lorcana -- uvx lorcana-mcp serve
Easiest is the one-click bundle. To wire it up by hand instead, edit claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\, or Settings → Developer → Edit Config):
{
"mcpServers": { "lorcana": { "command": "uvx", "args": ["lorcana-mcp", "serve"] } } }
Use "command": "lorcana-mcp", "args": ["serve"] if you installed with pip rather than uv. Fully quit and reopen Claude Desktop after saving.
Once the server is connected, just talk to Claude naturally. No slash commands needed.
Export your collection from TCGPlayer → My Collection → Export CSV, then:
"Enrich my collection at /Users/me/Downloads/Lorcana_063026.csv"
Claude will fetch card data from the APIs and write two files next to your input:
enriched_Lorcana_063026.csv — your collection with 10 new columnsdreamborn_Lorcana_063026.csv — ready to import at dreamborn.inkOn re-runs, pass the previous enriched file as a cache to skip already-seen cards:
"Enrich /Users/me/Downloads/Lorcana_new.csv using /Users/me/lorcana/enriched_Lorcana_old.csv as cache"
To refresh prices on demand without re-exporting from TCGPlayer:
"Re-enrich my collection at /Users/me/lorcana/enriched_Lorcana_063026.csv and refresh prices"
refresh_prices=True overwrites each row's TCG Market Price with a live tcgcsv.com lookup for that exact printing — useful when an enriched CSV's prices are stale.
"Look up Mirage - Super Recruiter"
"What are the stats on Alma Madrigal - Heart of the Family?"
"Is Will o' the Wisp legal in Core?"
Returns: ink color, cost, type, subtypes, STR/WIL/Lore, inkable status, keywords, full ability text, format legality, and a card image URL.
"Find the card 'goofy musketeer'"
"What's that card 'big pete'?"
"Look up 'elsa' — not sure which version"
Tokenizes the query and scores it against every card's name and subtitle, tolerating missing dashes, missing subtitles, word order, and minor typos. Returns full detail for a single confident match, a ranked top-3 with confidence scores when several cards are plausible (e.g. a bare name matching every printing of that character), or nothing if the query doesn't resemble any card.
"Show me all
冒頭だけを表示しています。続きはリポジトリで読めます