mcpdata Request an invite

Answers / Explainers

What is the difference between giving AI a file and giving it a database?

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

A file is read: the assistant takes in as much as fits and reasons over that. A database is queried: the assistant asks questions and the database computes the answers over every row. Files suit small documents; data you count, sum or compare belongs in a database.

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, how many orders in Demo.Orders were refunded, by region?
What your AI does: the tool call it makes for this prompt, and what came back
query(table_name="Demo.Orders", filters=[{"column": "status", "op": "eq", "value": "refunded"}], group_by=["region"], agg=[{"func": "count", "column": "order_id", "alias": "refunded_orders"}], sort=[{"column": "refunded_orders", "desc": true}]) → 3 rows
What you should get · the recipe's real result from its last run
regionrefunded_orders
Americas167,779
EMEA152,341
APAC80,113

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

With a file, the answer depends on how much of it the assistant read and how well it added up. With a database, it depends only on the query, which you can see and run again. A database also remembers: the data is there in the next conversation, for other people and for your other tools.

Related questions