Context7
Up-to-date docs for AI agents
Beschreibung vom Entwickler (englisches Original)
MCP server for Disney Lorcana TCG: enrich collections, search cards, build decks, audit data.
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
Du brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Öffne Claude Desktop → Settings → Developer → Edit Config und füge dies in claude_desktop_config.json ein
{
"mcpServers": {
"lorcana": {
"command": "uvx",
"args": [
"lorcana-mcp"
]
}
}
}Führe das in deinem Terminal aus
claude mcp add lorcana -- uvx lorcana-mcpIn .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"lorcana": {
"command": "uvx",
"args": [
"lorcana-mcp"
]
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"lorcana": {
"type": "stdio",
"command": "uvx",
"args": [
"lorcana-mcp"
]
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
Dieser Server läuft auf deinem Computer, und ChatGPT kann sich nur mit Servern im Internet verbinden. Wähle eine andere App.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Läuft auf deinem Computer; die Tool-Liste erscheint nach der Installation in deiner KI-App.
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 7. Nov. 2026
Der Registry-Name wurde mit dem GitHub-Konto IcaroBichir bestätigt, dem das Repo gehört
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieser Server läuft auf deinem Computer; es gibt keinen Endpunkt im Internet
Läuft auf deinem Computer und nutzt stattdessen lokale Einstellungen
Läuft auf deinem Computer; Tool-Listen können wir nur von Endpunkten im Internet lesen
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 1 von 1 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Die Registry nennt keinen erforderlichen Schlüssel, manche Server bitten dich aber bei der ersten Nutzung, dich anzumelden.
Er läuft auf deinem Computer. Deine KI-App startet ihn bei Bedarf, und die Daten laufen nicht über die Server des Entwicklers (außer der Server ruft selbst einen Onlinedienst auf).
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (2.6.1) kam vor 19 Tagen in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Außerdem brauchst du Python (uv) auf deinem Computer.
In derselben Kategorie: Context7, Codebase Memory, Exa
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
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.
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
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
Nur der Anfang wird gezeigt; den Rest findest du im Repo