lunchmoney-mcp: Instructions file for Claude Code

CLAUDE.md

lunchmoney-mcp CLAUDE.md is an instructions file for Claude Code from akutishevsky/lunchmoney-mcp. It costs 1,628 tokens per session, scanned A, original, MIT.

A project guide for an MCP server that connects AI tools to the LunchMoney personal-finance API, including its architecture, commands, tests, and implementation patterns.

In plain words
What is it for?
It helps add or modify finance-related tools, build the server, package it for Claude Desktop, run development inspection, format code, and execute tests.
Why use it?
It explains how this TypeScript service is built and tested, so an AI coding assistant can change it without overlooking its compilation and packaging requirements.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is akutishevsky/lunchmoney-mcp's own configuration. It tells Claude Code how to work on lunchmoney-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lunchmoney-mcp configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { formatData } from "../format.js";.

Reuse

Borrowing it

Nothing to install: this file belongs to akutishevsky/lunchmoney-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/akutishevsky/lunchmoney-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/akutishevsky/lunchmoney-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lunchmoney-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/akutishevsky/lunchmoney-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/akutishevsky/lunchmoney-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/akutishevsky/lunchmoney-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/akutishevsky/lunchmoney-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lunchmoney-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/akutishevsky/lunchmoney-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/akutishevsky/lunchmoney-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,628 This file is loaded in full into every session.
When invoked 1,628 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01628 $0.01628
Opus 5 $0.00814 $0.00814
Sonnet 5 $0.00326 $0.00326
Haiku 4.5 $0.00163 $0.00163

Measured 11d ago against content hash b7cd01199d2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

lunchmoney-mcp CLAUDE.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 11d ago.

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.

CLAUDE.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

MCP (Model Context Protocol) server for the LunchMoney personal finance API (v2). Provides 59 tools across 10 domains (transactions, categories, budgets, manual accounts, tags, recurring items, user, Plaid accounts, crypto, balance history). Uses stdio transport and is published to npm as @akutishevsky/lunchmoney-mcp.

Commands

  • npm run build — compile TypeScript and chmod the entry point

  • npm run build:mcpb — build + package as .mcpb for Claude Desktop

  • npm run dev — run with MCP Inspector (set LUNCHMONEY_API_TOKEN in the script first)

  • npm run format — run Prettier on the entire codebase

  • npm test — build, then run the test suite with Node's built-in runner

Tests live in test/*.test.mjs and are plain ESM JavaScript, not TypeScript: tsconfig.json sets rootDir: ./src, so tests can't be compiled by the main build. They import the compiled output from build/, which is why npm test builds first — that also makes the run a typecheck. Shared fixtures (sandbox directories, magic-byte samples, env-var juggling) live in test/helpers.mjs; use them rather than rolling new ones.

Coverage is currently limited to src/attachments.ts, the security-sensitive path from issue #16. The tool handlers themselves are still exercised manually via npm run dev with the MCP Inspector against a real LunchMoney account.

npm run lint is currently broken — typescript-eslint does not yet support TypeScript 7. This predates the test suite.

A husky pre-commit hook runs npm run format automatically before every commit.

Architecture

Entry point: src/index.ts — creates McpServer, registers all tool modules, initializes config, connects via StdioServerTransport.

Config: src/config.ts — singleton initialized at startup via initializeConfig(). Requires LUNCHMONEY_API_TOKEN env var. Base URL (https://api.lunchmoney.dev/v2) is hardcoded. Access via getConfig().

Read the full file on GitHub · 109 lines

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. 11d ago First seen · 109 lines · 1,628 tokens per session scan A b7cd01199d2b

Subscribe to this mod's changes

lunchmoney-mcp CLAUDE.md is an instructions file published in the GitHub repository akutishevsky/lunchmoney-mcp (103 stars, last pushed 1mo ago), licensed MIT. It adds 1,628 tokens to every session, about $0.0081 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens