mcpdata Request an invite

Answers / Explainers

What is MCP (Model Context Protocol)?

Recipe verified on Ran on the public demo (read-only)
Short answer

MCP is an open protocol that lets an AI assistant use outside tools and data: a server lists the tools it offers (with their arguments and descriptions), and the assistant calls them and reads the results. Claude, ChatGPT, Cursor, VS Code and others support it, so one server works with all of them.

Steps

  1. Connect your assistant to the public demo. It's a read-only instance with 10 million synthetic orders, so you can try this before you have your own. In Claude Code: 
    claude mcp add --transport http mcpdata-demo https://demo.mcpdata.org/mcp --header "Authorization: Bearer cdb_live_PkVoldus8qcE-hqffjajNZzQwiA7rTHMoR4RLSAxsCE"

    The key is public on purpose: it can only read the demo's sample data. For Claude Desktop, Cursor and other apps, see Connect your AI.

  2. Ask your question. Give your AI this prompt:
    Using mcpdata, what tools do you have, and what tables can you see?
What your AI does: the tool call it makes for this prompt, and what came back
list_tables() → 3 tables: Demo.Orders, Demo.Products, Demo.Customers
What you should get · the recipe's real result from its last run
tablerowslast_updated
Demo.Orders10,005,0002026-10-27 20:05:07.103000
Demo.Products2,0002026-10-27 19:50:37.321000
Demo.Customers200,0002026-10-27 19:50:36.983000

Synthetic data: the demo's orders are generated, not real customers.

Ask Claude with this prompt Ask ChatGPT with this prompt

The assistant needs mcpdata connected (step 1) to run the query.

Why this works

Before MCP every assistant needed its own plugin format. With MCP a database, a ticketing system or a file store publishes one server, and any MCP-capable assistant can use it. Below is a real exchange: the assistant asks the mcpdata server for its tables and gets a structured answer back, not a web page to read.

Related questions