EDHREC MCP Server
Enables Claude to access EDHREC's Commander deckbuilding data, including recommended cards, synergies, combos, and average decklists.
README
EDHREC MCP Server
A local MCP server that gives Claude access to EDHREC's Commander deckbuilding data — recommended cards, synergies, combos, and average decklists.
EDHREC has no official public API. This server calls the same JSON endpoints (json.edhrec.com) that edhrec.com's own frontend uses to render its pages. These endpoints are undocumented and unofficial — they may change or break without notice. No API key is needed.
Tools
edhrec_get_commander_recommendations— card recommendations for a commander, grouped by category (High Synergy, Top Cards, Creatures, etc.)edhrec_get_card_synergies— cards that synergize with a given (often non-commander) card, plus known combosedhrec_get_average_decklist— EDHREC's precomputed average 100-card decklist for a commander
Setup
1. Install dependencies
Requires Python 3.10+.
cd "edhrec_mcp"
pip install -r requirements.txt
2. Test it directly (optional)
python server.py
With no PORT environment variable set, this runs over stdio (for the MCP Inspector or a classic Claude Desktop config). You can also exercise it with the MCP Inspector:
npx @modelcontextprotocol/inspector python server.py
3. Register it as a connector in Cowork (this project)
Cowork's "Add custom connector" dialog only accepts a remote MCP server URL — it can't point at a local script. server.py runs over streamable-HTTP automatically whenever a PORT environment variable is present (which is how Render and most PaaS hosts tell an app what to bind to). That's what makes it deployable.
Deploy to Render (free tier):
- Push the contents of this
edhrec-mcpfolder to a new GitHub repo (the folder's contents should be the repo root —server.py,requirements.txt, andrender.yamlat the top level).cd "edhrec-mcp" git init git add . git commit -m "EDHREC MCP server" git branch -M main git remote add origin https://github.com/<your-username>/edhrec-mcp.git git push -u origin main - Go to render.com → sign in with GitHub → New → Blueprint → select your
edhrec-mcprepo. Render will readrender.yamland configure the service automatically. Click Apply. - Wait for the first deploy to finish (a few minutes). Render gives you a URL like
https://edhrec-mcp.onrender.com. - Sanity-check it's alive by visiting
https://edhrec-mcp.onrender.com/mcpin a browser — a 4xx/JSON error about missing headers is fine; that means the MCP endpoint is up. - In Cowork, open Settings → Connectors → Add custom connector, and paste:
- Name: EDHREC (or anything you like)
- Remote MCP server URL:
https://edhrec-mcp.onrender.com/mcp - Leave Advanced settings (OAuth) blank — this server has no auth.
- Save. The EDHREC tools should now show up as a connector you can enable in any conversation.
Note on the free tier: Render's free web services spin down after ~15 minutes of inactivity and take 30-60 seconds to wake back up on the next request (cold start).
Notes
- Card/commander names are converted to EDHREC's URL slug format internally (lowercase, punctuation stripped, spaces to hyphens). If a lookup fails, double-check the exact card name spelling — fuzzy matching isn't available the way Scryfall offers it.
- These endpoints are unofficial; please use them at a reasonable, interactive-use request rate.
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。
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。
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。
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。
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。
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。
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。