Dotplot Mcp

io.github.brownglassesPublished by GitHub account brownglassesv0.1.4Updated Oct 24, 2026

Product analytics for user flows: aha moments, retention, funnels, per-user dot plots. YC method.

VerifiedSTDIODesktop onlyProductivity & WorkflowData & Analytics

Overview

AI-generated overview

Lets an assistant analyze product usage data and produce per-user dot plot reports on retention, funnels, and aha moments.

What you can do
Dotplot MCP gives an assistant a product-analytics workflow built around per-user dot plots rather than aggregate charts. It finds your data, picks an event that represents user value, and writes a report covering retention, funnels, and aha moments. Slash commands cover a full analysis, finding and writing missing tracking code, and comparing against a previous report. The README states that code computes the numbers while the AI only interprets them.
When to use it
Useful for small products that want to see individual users instead of DAU/MAU charts, especially before reaching hundreds of users. Also suited to teams that have data in existing tables but no dedicated events table, or that want help adding missing logging. A bundled sample dataset lets you try the pipeline first.
Requirements
Runs locally over stdio as a PyPI package, started with uvx, so a Python runtime and uv/uvx are needed. No authentication, environment variables, or headers are declared. It reads your product data, and the README suggests cloning the repository and running sample scripts for a trial.
Before you install
The server reads your product data and the assistant may write tracking or logging code into your project, so review generated changes before committing. Reports are written to files and may be compared across runs. The README's setup instructions point to an external setup page and repository; verify those sources yourself before running anything.

Installation

In SourceWeft

  1. Open Dotplot Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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
Or do it by hand
bash
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:

sql
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.

No product to analyze yet? Try the sample
bash
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

MIT

Source: README.md at commit bc69a77

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.4LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts