On-Demand-Books

What is On-Demand-Books?

On-Demand-Books is an MCP server that helps AI agents find the perfect personalized puzzle book gift from a catalog of 100,853 customized books on the On-Demand-Books Shopify store.

Ask any AI assistant "find puzzle books for Susan" and it will return 9 personalized books (mazes, name-sudokus, and word searches across 3 difficulty levels) with direct Shopify purchase links.

How to use

Add the server to any MCP-compatible AI agent (Claude Desktop, Cursor, opencode, etc.):

{
  "mcpServers": {
    "On-Demand-Books": {
      "url": "https://on-demand-books-dq2yvpdh.fermyon.app/"
    }
  }
}

Then just ask your AI assistant: "I need a gift for my niece Susan who likes puzzles."

Tools

• search_books — Search the 100k+ personalized catalog by first name. Returns up to 9 matching books with Shopify purchase links, cover images, and ISBNs. Distinguishes exact matches from similar-name matches.
• suggest_names — Suggest popular first names for which books are available, optionally filtered by a prefix. Use when a buyer is unsure of a spelling or wants gift-recipient ideas.
• get_book — Re-resolve a single book's Shopify purchase URL from its product handle.

Key features

• No API key required — public, free, ready to use
• 100,853 personalized puzzle books across mazes, name-sudokus, and word searches
• Direct Shopify purchase links in every result
• UTM source tracking for marketing attribution
• Hosted on Fermyon Cloud as a WebAssembly component
• Built with the wasmcp toolkit

Use cases

1. Gift shopping — "Find puzzle books for my nephew David" → 9 personalized books, one click to buy
2. Name discovery — "What names start with 'Su'?" → Sue, Susan, Suzanne
3. Bulk gifting — Find personalized books for coworkers, students, or team members by name

FAQ

• Do I need an API key?

No. The server is public and free to use.

• What if a name isn't in the catalog?

The server suggests similarly-named books, or you can use suggest_names to find available names with the same prefix.

• Does it work with any AI agent?

Yes — any MCP client that supports the Streamable HTTP transport (Claude Desktop, Cursor, opencode, Cline, etc.)

• How do I track which channel drove sales?

Pass utm_source in the tool arguments (e.g. {"name": "Susan", "utm_source": "mcp.so"}) and Shopify Analytics will show sessions by source.