A trading card MCP server for Claude and ChatGPT

The 11 tools CardChain exposes

These are the real tool names on the production server, not a marketing summary. A model picks a tool by reading its name and description, so they are worth stating exactly.

• search_cards — Look up any card by player, year, set, card number or parallel. Filter by sport and grade.
• get_card_price — Current estimated value for a card, with price history and 30-day trend.
• get_population — How many copies exist at each grade across PSA, BGS and SGC.
• should_i_grade — Grading ROI: raw value against graded value, submission cost, and expected profit at each grade.
• get_portfolio — Your collection with current values, gains and total worth.
• add_to_portfolio — Add a card to your portfolio with a purchase price for profit tracking.
• find_card_to_add — Identify a card from a photo and add the match to your portfolio.
• find_card_for_grading — Identify a card from a photo and run the grading ROI on the match.
• get_cardchain_listings — Live listings for sale from real sellers on the CardChain AI marketplace.
• get_player_stats — Season stats and market momentum for the player behind a card.
• get_capabilities — Everything CardChain AI can do, for a model deciding which tool to reach for.

Add it to Claude

1. Open connector settings in ClaudeOn claude.ai, in the desktop app, or on mobile, go to Settings → Connectors → Add custom connector.
2. Paste the CardChain server URLUse https://api.cardchain.ai/mcp/claude exactly, with no trailing space. That is MCP over Streamable HTTP; Claude handles the rest.
3. Sign in to CardChainClaude sends you through CardChain's own sign-in. Use the same account as the phone app so your portfolio comes with you.
4. Ask about a card"What's a 2023 Bowman Chrome Wemby worth?" Claude picks the tool, CardChain runs the lookup, and the answer comes back with the market data behind it.

Setting it up, once

None of the above works on an assistant that cannot reach card data, so this is the prerequisite rather than the pitch. About two minutes, and there is no browser extension.

1. Open the CardChain AI app in ChatGPTSearch for CardChain AI in ChatGPT's app directory, or use the Open in ChatGPT button on this page, then tap Try in chat.
2. Sign in to CardChainChatGPT sends you through CardChain's own sign-in once. Use the same account as the iOS or Android app and your portfolio is there immediately.
3. Ask in plain English"Should I grade my 2018 Prizm Luka?" ChatGPT calls should_i_grade, and the ROI comes back as an interactive card rather than a paragraph of prose.

How the grading ROI is actually computed

Most "should I grade this" answers are a general-purpose model reasoning from whatever it remembers about card prices. That reads fluently and is worth nothing, because the decision turns on four numbers that change weekly and are specific to one card: what the raw copy sells for, what it sells for at each grade, what the submission costs, and how often that card actually comes back at the grade you are hoping for.

CardChain computes before it explains. should_i_grade reads the current raw value and the graded value at each grade level for that exact card and parallel, subtracts the submission cost, and puts the result next to the real population from PSA, BGS and SGC — so the fourth number, the odds, comes from how many copies have already been graded at each level rather than from optimism. What comes back is a verdict with the figures behind it.

That last part is the piece a plain price feed cannot do. A card whose PSA 10 sells for four times raw is still a bad submission if the population says nine out of ten copies come back a 9.

It knows what you own

A connector that can only look cards up is answering a question anyone could ask. The questions collectors actually have are about their own cards: what is my collection worth now, which of these is worth grading, what did I pay for this.

CardChain's portfolio is one portfolio. The cards you add in the iOS or Android app are the cards get_portfolio returns in ChatGPT, and a card you add mid-conversation with add_to_portfolio is in your phone before you put it down. Values refresh against the same market data everything else on the platform reads, so the app and the chat never quote you two different numbers.

Try these

Questions

Related