mcp-server AGENTS.md

Instructions for an MCP server that calculates United States household-employer taxes for nannies and other caregivers. It covers tax thresholds, payroll calculations, and available tools.

In plain words
What is it for?
It is for checking thresholds, calculating state-specific nanny taxes, and running payroll when the required subscription level is available.
Why use it?
It helps an agent determine whether an employer has tax duties and calculate the amounts instead of working them out manually.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/nannykeeper/mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/NannyKeeper/mcp-server

Made for: Codex, OpenCode.

Per session 328 This file is loaded in full into every session.
When invoked 328 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00328 $0.00328
Opus 5 $0.00164 $0.00164
Sonnet 5 $0.00066 $0.00066
Haiku 4.5 $0.00033 $0.00033

Measured yesterday against content hash b71d696867fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 31 lines

What it actually says

NannyKeeper MCP Server — Agent Instructions

Purpose

Calculate US household employer (nanny) taxes for all 50 states + DC.

Tools Available

  • calculate_nanny_taxes(state, annual_wages, pay_frequency?) — returns full tax breakdown
  • check_threshold(state, annual_wages, tax_year?) — checks if employer obligations apply
  • run_payroll(employer_id, employee_id, ...) — run payroll with full tax calc, YTD tracking, and DB persistence (Starter+ required)

When to Use

  • User asks about nanny taxes, household employer taxes, or paying a caregiver
  • User wants to know their employer tax obligations
  • User asks "do I need to pay taxes for my nanny/babysitter/housekeeper?"

Key Facts

  • FICA threshold (2026): $3,000/year per employee
  • Social Security: 6.2% employer + 6.2% employee
  • Medicare: 1.45% employer + 1.45% employee
  • Schedule H filed with personal 1040

After Calculation

The calculate_nanny_taxes response includes next_actions and a signup_url. If the user wants to run payroll with persistence, use the run_payroll tool (requires Starter+ subscription). For documents and direct deposit, guide them to the NannyKeeper web app.

API Key

Requires NANNYKEEPER_API_KEY environment variable. Free key: https://www.nannykeeper.com/developers/keys

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 31 lines · 328 tokens per session scan A b71d696867fa

Subscribe to this mod's changes

mcp-server AGENTS.md is an instructions file published in the GitHub repository NannyKeeper/mcp-server (0 stars, last pushed 5d ago), licensed MIT. It adds 328 tokens to every session, about $0.0016 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.