myfinance-mcp: Instructions file for Claude Code

CLAUDE.md

myfinance-mcp CLAUDE.md is an instructions file for Claude Code from alex-odoo/myfinance-mcp. It costs 791 tokens per session, scanned B, original, MIT.

A set of instructions for AI coding agents working on the myfinance-mcp personal-finance server.

In plain words
What is it for?
Understanding the repository, running local development and end-to-end tests, and following the maintainer’s controlled deployment process.
Why use it?
It gives the agent the project context, technology choices, local-development commands, testing steps, and deployment restrictions it needs to work safely.

Instructions file for Claude Code

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

This is alex-odoo/myfinance-mcp's own configuration. It tells Claude Code how to work on myfinance-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 myfinance-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alex-odoo/myfinance-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/alex-odoo/myfinance-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/alex-odoo/myfinance-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 myfinance-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alex-odoo/myfinance-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/alex-odoo/myfinance-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alex-odoo/myfinance-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alex-odoo/myfinance-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 myfinance-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/alex-odoo/myfinance-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alex-odoo/myfinance-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 791 This file is loaded in full into every session.
When invoked 791 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00791 $0.00791
Opus 5.5 $0.00316 $0.00316
Sonnet 5.5 $0.00158 $0.00158
Haiku 4.5 $0.00079 $0.00079

Measured 5d ago against content hash 9c34b9e6fba8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

myfinance-mcp CLAUDE.md scanned grade B with 1 finding 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

(chmod 600) - not in repo, not rsynced.
CLAUDE.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - MyFinance MCP

Guidance for AI coding agents working in this repo.

What it is

Personal finance tracking through a remote MCP server. The user's own AI client (Claude, ChatGPT, Cursor) is the UI: log expenses by voice or receipt photo, ask for stats in plain language. No app, no forms. The server owns the DATA and the MATH; the AI client owns the ADVICE.

Stack

  • Bun + TypeScript + @modelcontextprotocol/sdk (Streamable HTTP, stateless) + Express
  • OAuth 2.1 - PKCE + dynamic client registration
  • Prisma + Postgres (hosted instance: Supabase, eu-central-1)
  • Docker behind nginx
  • Hosted instance: https://myfinance-mcp.com (MCP endpoint POST /mcp, Bearer token)

Self-hosting for a person (not a maintainer): docs/SELF_HOSTING.md; never deploy.sh.

Deploy (maintainer only - never manual)

./deploy.sh "what changed"

One-way Mac -> server: local bun run build + bun run e2e gate, commit + push main, rsync, docker compose build && up -d, nginx sync, health check (/health must report the deployed commit). Every step aborts the deploy on failure. Never edit code on the box. Secrets live in app.env on the server (chmod 600) - not in repo, not rsynced.

Local dev

bun install
cp .env.example .env   # fill in your values
bun run dev            # server on :8788
bun run e2e            # self-contained E2E proof on a LOCAL test DB (E2E_DATABASE_URL)
bun run e2e https://myfinance-mcp.com      # same suite vs prod (E2E_EMAIL/E2E_PASSWORD)
bun run lint

Password hash: bun -e "console.log(await Bun.password.hash(process.argv[1]))" 'pw'

Database

Schema changes ship with ./deploy.sh: it runs prisma db push (non-destructive) and prisma/rls.sql on the hosted database through an SSH tunnel via the app server, the only address that database accepts. Prisma creates tables with RLS off, and a public-schema table without RLS is exposed through the Supabase Data API to anyone with the anon key (see the header of that file).

Read the full file on GitHub · 71 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. 5d ago Changed · +2 lines · +25 tokens per session 9c34b9e6fba8
  2. 1mo ago Changed · +2 lines · +28 tokens per session 2ef7de2089a8
  3. 1mo ago Changed · +1 lines · +18 tokens per session 2a67d4e9d26d
  4. 2mo ago First seen · 66 lines · 720 tokens per session scan B cea7db06ad58

Subscribe to this mod's changes

myfinance-mcp CLAUDE.md is an instructions file published in the GitHub repository alex-odoo/myfinance-mcp (2 stars, last pushed 5d ago), licensed MIT. It adds 791 tokens to every session, about $0.0032 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

myfinance-mcp CLAUDE.md compared with instructions from other repositories

myfinance-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
myfinance-mcp CLAUDE.mdalex-odoo/myfinance-mcpInstructions file25d agoMITB791Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124ktodayMITA2,981Codex, OpenCode