mcpdata Request an invite

Answers / Explainers

What is the difference between an MCP server and an API?

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

An API is made for programs that already know how to call it; an MCP server is made for an AI to discover and use by itself. It describes each tool in words (what it does, what each argument means), so the assistant can pick the right one, and the protocol is the same for every server.

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, describe the Demo.Orders table.
What your AI does: the tool call it makes for this prompt, and what came back
describe_table(table_name="Demo.Orders") → 15 columns, 10,005,000 rows
Ask Claude with this prompt Ask ChatGPT with this prompt

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

Why this works

mcpdata has both: an HTTP API (/api/v1/...) for programs and an MCP server (/mcp) for assistants, over the same tables and the same keys. The MCP tools are shaped for an AI: structured arguments instead of free-form SQL, results capped with a flag saying when there's more, and guides the assistant reads before writing a view.

Related questions