mcpField
H
HourLedger — Work Hours & Overtime Calculator

HourLedger — Work Hours & Overtime Calculator

Local
hourledger.comFinance2Updated 18w ago

About HourLedger — Work Hours & Overtime Calculator

HourLedger is an MCP server for calculating work hours, overtime, and gross pay. It is intended for workers and payroll workflows that need calculations under tested US federal and state rulesets, with shift, rounding, and workweek options.

Key features

  1. 01Work-hour and gross-pay calculations
  2. 02Federal and four state rulesets
  3. 03Overnight shift handling
  4. 04Configurable rounding and workweek start
  5. 05Quick time-and-a-half calculation

Use cases

  1. 01Calculate weekly pay from clock entries
  2. 02Check overtime under a state ruleset
  3. 03Estimate overtime pay from rate and hours

MCP support

Exposes `calculate_work_hours` and `time_and_a_half` as tools for MCP clients. The first returns regular, overtime, and double-time splits with gross pay.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"hourledger": {
"command": "npx",
"args": [
"-y",
"hourledger-mcp"
]
}
}
}
Run commandnpx -y hourledger-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmhourledger-mcp1.0.2

Tools

2

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
entriesarrayYes
hourlyRatenumberYes
rulesetenumNofederal | california | alaska | colorado | nevada
workweekStartintegerNo0=Sunday … 6=Saturday
roundingenumNonone | nearest_5 | nearest_15 | nearest_tenth
nvDailyOtbooleanNoNevada only: override the rate-based daily-OT eligibility check

Details

From the project README

hourledger-mcp

An MCP server that calculates work hours, overtime, and gross pay — wrapping the same tested rules engine that powers HourLedger, a suite of free, no-sign-up work-hours calculators.

Tools

calculate_work_hours

Takes clock in/out entries (with unpaid breaks), an hourly rate, and a ruleset; returns the per-day and total regular / overtime / double-time split plus gross pay.

Supported rulesets, each covered by the automated test suite:

RulesetRule
federal1.5× past 40 h/week (FLSA)
california1.5× past 8 h/day, 2× past 12 h/day, 7th-day rule, no pyramiding (Labor Code §510)
alaska1.5× past 8 h/day or 40 h/week (AS 23.10.060)
colorado1.5× past 12 h/day or 40 h/week (COMPS Order)
nevadadaily 8 h rule only below 1.5× minimum wage — applied automatically from the rate (NRS 608.018)

Handles overnight shifts, per-entry rounding policies (exact / 5 min / 15 min / 0.1 h), and configurable workweek start day.

time_and_a_half

Quick 1.5× rate and overtime-pay calculation from a rate and OT hours.

Setup

Claude Desktop / Claude Code
{
  "mcpServers": {
    "hourledger": {
      "command": "npx",
      "args": ["-y", "hourledger-mcp"]
    }
  }
}

Or with Claude Code: claude mcp add hourledger -- npx -y hourledger-mcp

Example

"How much do I make this week? I worked Monday to Thursday 7am–5pm at $19/hour in Nevada."

The model calls calculate_work_hours with the four 10-hour entries and gets back the correct Nevada answer ($19 ≥ $18 cutoff → weekly rule only → 40 regular hours, no OT), with day-by-day detail.

Interactive calculators

Prefer a UI? Every ruleset has a free, no-sign-up calculator at hourledger.com:

Disclaimer

General information, not legal or payroll advice. Exemptions and local rules vary — verify disputed pay with your state labor agency or a qualified professional.

Development

The pay-rules engine (src/engine.ts + its 27 tests) is mirrored from the HourLedger site project, where rule changes land first. npm test runs the full suite; prepublishOnly enforces tests + build before any publish.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.