Lapsewatch

io.github.GillMacedoPublished by GitHub account GillMacedov0.1.0Updated Nov 3, 2026

Find customers who stopped buying, and the revenue at risk, from an orders CSV on your machine.

VerifiedSTDIODesktop onlyData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Reads a local orders CSV and tells an assistant which customers are at risk or lost, plus the yearly revenue at stake.

What you can do
  • Analyze an orders CSV for churn: list at-risk, lost, new and one-time customers by priority, with yearly revenue at risk, repeat rate and revenue concentration.
  • Inspect an unfamiliar CSV: show which columns are detected and how many rows can be read, without returning row contents.
  • Both tools are read-only and work offline on a file on your machine.
When to use it
Useful when you have an orders export (for example from a store or billing system) and want retention or win-back lists, revenue-at-risk estimates, or a quick read on repeat-customer rate and dependence on top customers.
Requirements
Runs locally over stdio via npx, so Node.js is needed; alternatively build the Go binary with Go 1.27 or newer. No account, API key or network access is required. The CSV must be on the local machine, up to 50 MB, with recognizable date, customer and amount columns (custom column names can be mapped).
Before you install
The check tool returns customer names or emails to the MCP client, so they reach whichever AI model you use; the CLI keeps data local. Results are estimates based on each customer's median order gap, and one-off or seasonal buyers can look lapsed. It reads CSV only, does not convert currencies, and has been tested only on made-up data. Follow local marketing and privacy rules before emailing customers from these lists.

Installation

In SourceWeft

  1. Open Lapsewatch 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

lapsewatch: find customers who stopped buying

[npm] [CI] [MIT license] [MCP Registry]

Customer retention and churn analysis from an orders CSV: see who's at risk, who you've lost, and how much yearly revenue is in danger. For e-commerce stores, service businesses and small B2B companies.

Keeping a customer usually costs less than finding one, but nobody notices when a regular quietly stops ordering. lapsewatch compares each customer with their own buying pattern, so someone who orders monthly is flagged sooner than someone who orders twice a year. It's an MCP server and a single Go binary, with no account, no API key and no network access.

What you can ask your agent

  • "Which customers have stopped buying?"
  • "Who should I contact first to win back revenue?"
  • "How much yearly revenue is at risk?"
  • "What's my repeat customer rate, and how much do I depend on my top customers?"

Install

As a Claude Code plugin, which adds the MCP server and a skill that tells Claude when to use it. You need Node, which runs the server through npx:

claude plugin marketplace add GillMacedo/lapsewatchclaude plugin install lapsewatch@lapsewatch-marketplace

For other MCP clients:

json
{  "mcpServers": {    "lapsewatch": {      "command": "npx",      "args": ["-y", "lapsewatch", "serve"]    }  }}

Or build the binary with Go 1.27 or newer:

go install github.com/GillMacedo/lapsewatch@latest

Usage

Without installing anything, run npx lapsewatch check orders.csv. This example uses the made-up file in examples/:

$ go run . check examples/orders.csvAs of 2026-09-27: 8 customers, 75.0% bought more than once, 14598.00 revenue, top 10% bring in 49.3%AT RISK: contact these first (2)  [email protected]  197 days since last order, usually every 60  worth 5475.00 a year  [email protected]  92 days since last order, usually every 30  worth 3771.67 a yearLOST (1)  [email protected]  297 days since last order, usually every 20  worth 1368.75 a yearONE-TIME (1)  [email protected]  397 days since their only order  spent 60.003 active, 1 new.SKIPPED row 68: no valid date, customer or amount9246.67 a year at risk from 2 customers.

Add --as-of 2026-12-31 to measure from a specific date, --top 50 to list more customers, and --json for machine-readable output.

How it decides

StatusRule
ActiveOrdered within twice their usual gap
At riskPast twice their usual gap, and at least 30 days since their last order
LostPast four times their usual gap, and at least 30 days since their last order
NewOne order in the last 90 days
One-timeOne order, more than 90 days ago

The usual gap is the median number of days between a customer's orders. Yearly value is their average order times 365 divided by that gap, so it's an estimate. Rows on the same day count as one order, and refunds reduce totals without counting as orders.

MCP tools

ToolWhat it does
customers_check_lapsedReturns the summary and customers by priority, with a limit for large files
customers_inspect_csvShows detected columns and row counts, without row contents

Both are read-only, and neither can contact anyone. customers_check_lapsed returns customer names or emails to the MCP client, so they reach whichever AI model you use. The CLI keeps everything on your machine.

FAQ

How do I find inactive customers? Export your orders as CSV and run npx lapsewatch check orders.csv.

Does it work with Shopify, WooCommerce or Stripe exports? It reads CSV and recognizes common column names such as Email, Total and Created at, and you can name others with --columns date=When,customer=Who,amount=Sum. It doesn't connect to those platforms, and it hasn't been tested on each one's real exports yet.

Should I use names or emails? Emails work best, because it treats each distinct value as one customer.

Limits

  • It finds who to look at, and can't tell why someone stopped. A one-off need or a seasonal buyer can look lapsed.
  • A customer under two names or emails counts as two customers. samecontact can help clean a list first.
  • It doesn't convert currencies.
  • It reads CSV only, up to 50 MB.
  • If you email customers from these lists, follow your local marketing and privacy rules.
  • So far it has been tested on made-up data, not real exports. If yours fails, please open an issue with the column headers, not your data.

Contributing

Contributions are welcome, from people and from people working with AI agents. See CONTRIBUTING.md. Good first issues:

  • Add column names from more platforms and languages
  • Add --out to write a win-back list to a CSV
  • Add seasonal buyer detection
  • Add a cohort retention table
  • Add a plugin icon

How pull requests work

  1. Open a PR. Fork the repo, work on a branch, and keep it to one change. Write a title that says what changes for users, because it becomes the changelog line: feat: goes under Added and fix: under Fixed.
  2. Automatic check. Code changes need tests, and make test must pass. Changes over 30 lines need a linked open issue (Closes #<number>), and a PR can have at most 800 changed lines. If something is missing, a comment tells you what to fix.
  3. Review. Claude reviews each PR automatically. Code PRs also get a security review and are tested in a sandbox. The review then merges the PR or asks for changes. PRs that change CI, agent settings, npm or Python dependencies, vendored code or build files can't be merged this way, and a comment says so. The same goes for anything the security review doesn't clear.
  4. Release. A merge that changes what users install becomes a new version within about two hours, with a GitHub Release and, if the project has one, its npm package. Docs and CI changes wait for the next release.

AI disclosure

This project was largely generated with Claude Code and reviewed by its maintainer.

About me

I'm Giulliano Macedo, and I build developer tools at GoTech Solutions. Follow along or get in touch:

If lapsewatch helped you win a customer back, a star helps others find it.

MIT licensed.

Built by Giulliano Macedo, GoTech Solutions · LinkedIn · X

Source: README.md at commit 49960cb

Tools

2

customers_check_lapsed

Find customers who stopped buying

Finds at-risk and lost customers in an orders CSV by comparing each customer with their own buying pattern, with yearly revenue at risk, repeat rate and revenue concentration. Use for customer retention, churn analysis, or win-back lists. Read-only, and never uses the network. Results include customer names or emails from the file, so they reach the model. It can't contact anyone.

Parameterspathrequiredas_oflimitcolumnsdate_format

customers_inspect_csv

Inspect an orders CSV

Shows which columns lapsewatch detects in an orders CSV and how many rows it can read, without returning row contents. Use if the file is unfamiliar or a check failed.

Parameterspathrequired

Version history

1
  1. v0.1.0LatestOct 31, 2026

Score

90% 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
  • 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 listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts