mcp-scryfall
MCP server for live Magic: The Gathering card lookup via the Scryfall API. Grounds card references against live Scryfall data, with tools for exact, fuzzy, and search queries.
README
mcp-scryfall
MCP server for live Magic: The Gathering card lookup via the Scryfall API. Hand-rolled with the MCP TypeScript SDK, not a wrapper around an existing package.
LLMs confidently misremember card names, costs, and rules text. This grounds every card reference against live Scryfall data. I use it daily for deckbuilding.
Tools
| Tool | What it does |
|---|---|
card_named |
Exact-name lookup (optional set code). Full card object. |
card_fuzzy |
Fuzzy-name lookup. Handles typos and partial names. |
card_search |
Scryfall query-syntax search. Returns compact summaries by default (pass full: true for raw objects). |
card_random |
A random card, optionally filtered by a query. |
bulk_default |
Lists Scryfall bulk-data endpoints for offline corpus building. |
Install
git clone https://github.com/haksanlulz/mcp-scryfall
cd mcp-scryfall
npm install
Runs directly with tsx; no build step.
Use it from an MCP client
Add it to your client's MCP config (e.g. Claude Desktop's claude_desktop_config.json):
{
"mcpServers": {
"scryfall": {
"command": "npx",
"args": ["tsx", "/absolute/path/to/mcp-scryfall/index.ts"],
"env": { "SCRYFALL_CONTACT": "you@example.com" }
}
}
}
SCRYFALL_CONTACT is optional; it is added to the User-Agent per Scryfall's API guidelines.
Example
card_search with q = "c:rb cmc<=2 t:creature o:haste" returns compact rows plus paging metadata:
{
"total_cards": 42,
"has_more": true,
"page": 1,
"data": [
{ "name": "Ash Zealot", "mana_cost": "{R}{R}", "type_line": "Creature — Goblin Berserker", "cmc": 2, "set": "rtr" }
]
}
Pass full: true to get the raw Scryfall objects instead.
Develop
npm test # MCP-layer tests over an in-memory transport (fetch mocked, no network)
npm run smoke # hit the live Scryfall API once per tool
npm run typecheck
API etiquette
Follows Scryfall's guidelines: a 100 ms delay between requests, a descriptive User-Agent, and Accept: application/json.
License
MIT © Abishai James. Card data © Scryfall; this project is unofficial and not affiliated with Scryfall or Wizards of the Coast.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。