finance-mcp-server: Instructions file for Claude Code

CLAUDE.md

finance-mcp-server CLAUDE.md is an instructions file for Claude Code from PavelKosik/finance-mcp-server. It costs 911 tokens per session, scanned A, original, MIT.

A project instruction file for Claude Code describing a personal-finance MCP server. The server exposes a SQLite database—a file-based database—to an AI assistant for working with accounts, transactions, budgets, debts, investments, taxes, and goals.

In plain words
What is it for?
Developing, testing, and extending the finance server, including its database schema, CSV imports, and tax calculations.
Why use it?
It gives the coding assistant the project's layout, conventions, and database patterns, reducing guesswork when changing the code.

Instructions file for Claude Code

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

This is PavelKosik/finance-mcp-server's own configuration. It tells Claude Code how to work on finance-mcp-server 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 finance-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PavelKosik/finance-mcp-server. 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/PavelKosik/finance-mcp-server/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/PavelKosik/finance-mcp-server

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 finance-mcp-server CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pavelkosik/finance-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/pavelkosik/finance-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 911 This file is loaded in full into every session.
When invoked 911 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 $0.00911 $0.00911
Opus 5 $0.00456 $0.00456
Sonnet 5 $0.00182 $0.00182
Haiku 4.5 $0.00091 $0.00091

Measured 8d ago against content hash 95693e42aa67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

finance-mcp-server 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 8d 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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project handbook for Claude Code (and any AI assistant) working in this repository. This project was built with Claude Code, and this file is the source of truth for how to extend it.

What this is

A Model Context Protocol (MCP) server that exposes a personal-finance SQLite database as typed, schema-validated tools an AI assistant (e.g. Claude Desktop) can call directly — accounts, transactions, budgets, debts, investments, tax estimates, and goals over natural language.

It is a clean, self-contained reference implementation: it ships with no data and no secrets, just the schema, tool definitions, and server scaffolding. See README.md for the full tool table and the Claude Desktop wiring.

Layout

index.js              # MCP server entry point — registers every tool module over stdio
db.js                 # SQLite connection (better-sqlite3); path from DATABASE_PATH env var
schema/schema.sql     # Consolidated schema (no data)
scripts/init-db.js    # Creates an empty database from the schema
lib/
  csv-parser.js       # Tolerant bank-CSV parser (pure, unit-tested)
  tax-calc.js         # Tax-estimation logic (pure, unit-tested)
tools/                # One module per domain, each exporting register(server)
  settings.js  accounts.js  transactions.js  categories.js  debts.js
  budget.js    investments.js  tax.js  health.js  goals.js  actions.js  broker.js
test/                 # Unit tests for the pure lib/ functions

The core pattern

Every domain is a module that exports a single register(server) function. Inside, each tool is declared with a Zod schema for its inputs and a handler that runs parameterized SQL through db.js and returns its result as JSON text content (the standard MCP shape).

Adding a tool (the common task):

  1. Pick (or add) the right module in tools/.
  2. Declare the tool inside that module's register(server) with a Zod input schema.
  3. Use parameterized queries via the shared db — never string-concatenate user values into SQL.
  4. If it's bulk (import/sync), wrap writes in a single transaction so a failure leaves the DB unchanged.
  5. If you add a new module, register it in index.js.
  6. Update the tool table in README.md.

Read the full file on GitHub · 64 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. 8d ago First seen · 64 lines · 911 tokens per session scan A 95693e42aa67

Subscribe to this mod's changes

finance-mcp-server CLAUDE.md is an instructions file published in the GitHub repository PavelKosik/finance-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 911 tokens to every session, about $0.0046 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.

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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens