mcpdata Request an invite

Answers / Explainers

What is a context window and why does it limit data analysis?

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

The context window is how much text a model can hold at once: the conversation, files and tool results together. A large table doesn't fit, and what does fit crowds out everything else. A database keeps the data outside the window, so only the answer to each question has to fit.

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, total revenue by channel in Demo.Orders.
What your AI does: the tool call it makes for this prompt, and what came back
query(table_name="Demo.Orders", group_by=["channel"], agg=[{"func": "sum", "column": "revenue", "alias": "revenue"}, {"func": "count", "column": "order_id", "alias": "orders"}]) → 3 rows
What you should get · the recipe's real result from its last run
channelrevenueorders
Partner643,704,2381,201,830
Store1,768,785,2243,301,229
Online2,951,801,4565,501,941

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

Demo.Orders has 10 million rows: far more than any context window. The query below reads all of them in the database and returns three rows, a few hundred characters, to the assistant. That is the whole trick: move the question to the data, not the data to the question.

Related questions