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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.