Skip to main content
Glama
GillMacedo

latepayers

by GillMacedo

latepayers: accounts receivable aging report from an invoice CSV

npm CI MIT license MCP Registry

See who owes you money, how late each invoice is, and who to chase first. For freelancers, small businesses and bookkeepers tracking overdue invoices in spreadsheets.

Late payments quietly drain cash flow. latepayers reads an invoice export as CSV and builds an AR aging report with the standard buckets, per customer, ranked by overdue money and age. It also shows how late each customer usually pays. 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

  • "Who owes me money, and how late are they?"

  • "Which overdue invoices should I chase first?"

  • "Build an accounts receivable aging report."

  • "Which customers always pay late?"

Related MCP server: DataClaw MCP Server

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/latepayers
claude plugin install latepayers@latepayers-marketplace

For other MCP clients:

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

Or build the binary with Go 1.27 or newer:

go install github.com/GillMacedo/latepayers@latest

Usage

Without installing anything, run npx latepayers check invoices.csv. It uses today's date unless you pass --as-of. This example uses the made-up file in examples/:

$ go run . check examples/invoices.csv --as-of 2026-10-31
As of 2026-10-31: 5745.50 open, 3745.50 overdue (65.2%)
not due: 2000.00 | 1-30: 500.00 | 31-60: 975.00 | 61-90: 0.00 | 90+: 2270.50
Chase first:
  Example Supplies Ltd  1700.00 overdue of 1700.00 open, oldest 92 days
    INV-2001  1200.00  due 2026-07-31  92 days late
    INV-2002  500.00  due 2026-10-01  30 days late
  Demo Bakery  620.00 overdue of 620.00 open, oldest 122 days
    INV-2009  620.00  due 2026-07-01  122 days late
  Fictional Cafe  450.50 overdue of 450.50 open, oldest 139 days, usually pays 25.0 days late
    INV-2003  450.50  due 2026-06-14  139 days late
  Sample Widgets  975.00 overdue of 2975.00 open, oldest 42 days, usually pays 3.0 days early
    INV-2007  975.00  due 2026-09-19  42 days late
    INV-2006  2000.00  due 2026-11-09  not late
CREDIT  INV-2010  -75.00
SKIPPED row 13: no customer, amount or date

Add --terms 45 to set payment terms for invoices with no due date, and --json for machine-readable output.

How it calculates

Value

Rule

Open amount

The balance column if there is one, otherwise total minus paid

Due date

The due date column, otherwise invoice date plus payment terms (default 30 days)

Buckets

Not due, 1-30, 31-60, 61-90 and 90+ days past due

Chase first

Ranked by the sum of each overdue amount times its days overdue

Usual lateness

The average of paid date minus due date, if the file has paid dates

Negative balances are listed as credits and left out of the totals. Repeated invoice numbers and mixed currencies produce warnings.

MCP tools

Tool

What it does

receivables_aging_report

Returns totals, buckets and customers by priority, with a limit for large files

receivables_inspect_csv

Shows detected columns and row counts, without row contents

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

FAQ

What is an AR aging report? It groups unpaid invoices by how many days past due they are, so you can see how much money is at risk and who to contact.

Does it work with QuickBooks, Xero or FreshBooks exports? It reads CSV and recognizes common column names such as Balance Due, and you can name others with --columns customer=Who,amount=Sum. It doesn't connect to those products, and it hasn't been tested on each one's real exports yet.

Can it send payment reminders? No. It tells you who to contact, and you or your agent can draft messages for you to approve.

Limits

  • This helps you manage collections and isn't accounting or legal advice.

  • It's only as accurate as the export, so check balances before contacting a customer.

  • It doesn't apply credits to invoices, and doesn't convert currencies.

  • It treats each distinct customer name as one customer.

  • It reads CSV only, up to 50 MB.

  • 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 accounting tools and languages

  • Add --out to write the report to a CSV

  • Add Days Sales Outstanding (DSO) to the summary

  • Add a by-invoice view sorted by days late

  • Add a plugin icon

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 latepayers helped you get paid, a star helps others find it.


MIT licensed.

Built by Giulliano Macedo, GoTech Solutions · LinkedIn · X

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    An API-based accounting analysis tool that identifies financial anomalies like unusually large transactions and duplicate payments from CSV datasets. It allows AI agents to perform automated financial auditing and transaction analysis through structured tool endpoints.
    -
  • F
    license
    Not graded
    quality
    C
    maintenance
    AI-first CSV analysis tool that enables AI agents to analyze, query, and audit large CSV files directly within conversations, turning raw data into actionable insights.
    2
    -
  • A
    license
    Not graded
    quality
    C
    maintenance
    Lets a user ask what their business is owed, who to chase first, and get a chase email drafted in their own voice, via tools for weekly totals, chase queues, customer history, due-soon invoices and insights. Every tool only reads or returns a draft, so nothing can be sent.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables users and AI agents to reconcile CSV bank statements against invoices or bills by matching amounts and references, then sorting each line into matched, likely, review, or unmatched groups with reasons. It exposes read-only tools for matching files and inspecting detected CSV columns and row counts.
    MIT