Dotplot Mcp

Dot Plot MCP

See individual users, not aggregate charts.

English | 한국어

[report]

Install

Paste this to your agent and it sets everything up:

Set up Dotplot (MCP + skills) — instructions are here https://dotplot-reports.vercel.app/setup.md

claude mcp add --scope user dotplot -- uvx dotplot-mcp

Use

Say this in any project:

"Analyze my product"

You get the report above. That's it.

Or use the slash commands:

/dotplot-analyze-product    full analysis and report/dotplot-add-tracking       find and write the logging you're missing/dotplot-whats-changed      compare with the previous report

Claude finds your data, picks the action that means "this user got value", and writes the report. No events table needed — your orders table already is one:

SELECT user_id, created_at::date AS date, 'purchase' AS event FROM ordersUNION ALLSELECT user_id, added_at::date, 'add_to_wishlist' FROM wishlist_items

Nothing tracked yet? Say "add the tracking I'm missing" and Claude reads your code, writes the logging that's absent, and tells you when to come back.

git clone https://github.com/brownglasses/dotplot-mcp && cd dotplot-mcpuv run sample_data.py   # 40 fake users with a pattern planted in themuv run harness.py       # watch the whole pipeline run

Why this exists

DAU/MAU charts go "up and to the right" as long as new users arrive — even when nobody stays. Until you have hundreds of users, the most informative dashboard is YC's dot plot (David Lieb): one row per user, one cell per day.

Four rules keep it honest:

• Code computes, AI only interprets — same data, same numbers, every time
• Small samples withhold judgment — under 5 users in a group, it says nothing
• Correlation isn't cause — every finding ships with "test this before you believe it"
• Vanity metrics are refused — pick open_app as your value event and the code says no

Reports come out in your language (English, 한국어, 日本語 built in; anything else translated on the fly with the numbers verified intact).

More

• What each tool does, and the anonymous benchmark
• How it's built

MIT