gnucash-mcp: Instructions file for Claude Code

CLAUDE.md

gnucash-mcp CLAUDE.md is an instructions file for Claude Code from ninetails-io/gnucash-mcp. It costs 8,005 tokens per session, scanned A, original, MIT.

A contributor guide for an MCP server that lets AI assistants work with GnuCash books stored in SQLite. It explains the project’s structure, architecture, tools, and testing approach.

In plain words
What is it for?
Understanding the codebase, adding or updating GnuCash operations, and running unit or integration tests. GnuCash is accounting software, and MCP is a standard way for AI assistants to use external tools.
Why use it?
It gives contributors the background needed to change the code safely instead of guessing how the server is organized or what its parts do.

Instructions file for Claude Code

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

This is ninetails-io/gnucash-mcp's own configuration. It tells Claude Code how to work on gnucash-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 gnucash-mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ninetails-io/gnucash-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ninetails-io/gnucash-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,005 This file is loaded in full into every session.
When invoked 8,005 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 $0.08005 $0.08005
Opus 5 $0.04002 $0.04002
Sonnet 5 $0.01601 $0.01601
Haiku 4.5 $0.00800 $0.00800

Measured 5d ago against content hash a5776b3292c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gnucash-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 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.

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 · 656 lines

How it starts

The opening of the file, as written. The whole thing — 656 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GnuCash MCP Server — Contributor Guide

AI-facing orientation for contributors (human or AI) working on this codebase. See README.md for end-user usage and CHANGELOG.md for the per-release history.

Local working notes specific to the maintainer live in CLAUDE.local.md (not in version control).


Project at a glance

An MCP server that exposes a GnuCash SQLite book to AI assistants as a set of typed tools. Read and write transactions, run reports, manage scheduled transactions, budgets, investment lots, and a full business module (customers, vendors, employees, invoices, bills).

Tech stack:

  • Python 3.10+
  • piecash — GnuCash SQLite ORM
  • MCP Python SDK (mcp[cli])
  • SQLAlchemy under piecash; direct Core access where the ORM blocks us
  • pytest for unit + integration coverage

How the codebase reached its current shape

A few architectural moves shaped the present structure. The full release-by-release history is in CHANGELOG.md; what follows is the arc, not the chronicle.

  • Single-file → modular mixins. Early versions kept everything in one book.py. As the surface grew (reconciliation, reporting, budgets, scheduling, investments, business), the monolith was split into per-area mixins composed via build_book_class. Tools moved alongside under tools/<area>.py. Disabling a module via --modules skips both the mixin and the tool registration cleanly.
  • Lazy load with a registry. TOOL_MODULES in server.py is the single source of truth for which tools belong to which module. _lazy_load_tool_module(name) imports tools/<name>.py only when the module is enabled, then _apply_module_filter removes anything registered that isn't in TOOL_MODULES[<name>]. A test in tests/test_modules.py::TestToolFileVsModulesMapping locks the contract — it catches the bug class where a new tool gets the @mcp.tool() decoration but is forgotten in TOOL_MODULES.
  • Multi-currency rebuild. Originally USD-was-everywhere assumed. When the first non-USD-default book showed up, a class of bugs surfaced where reports summed raw split.quantity across commodities, prices defaulted to USD even for currency arguments, and FX gain/loss from rate drift wasn't recognized. The fix threaded _split_in_default_currency (or equivalent factor map) through every aggregation path, made create_price default to the book's default currency, and added realized FX recognition on cross-currency invoice payment.
  • Dashboard as a work queue. get_book_summary started as a status snapshot and evolved into the LLM's first-call orientation surface. It now surfaces net-worth trajectory, runway, monthly net income, budget pacing, reconciliation backlog with split counts, warnings, and upcoming scheduled transactions — answering "what do I need to do next" in one call.
  • Audit log dispatcher. Originally a 380-line if/elif chain; flattened into a (entity_type, operation) → formatter dispatch table. Adding a new entity-operation pair is one row in the table plus a small formatter function.

Read the full file on GitHub · 656 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 · +79 lines · +1,117 tokens per session a5776b3292c7
  2. 9d ago First seen · 577 lines · 6,888 tokens per session scan A a0c8fc22abe4

Subscribe to this mod's changes

gnucash-mcp CLAUDE.md is an instructions file published in the GitHub repository ninetails-io/gnucash-mcp (66 stars, last pushed yesterday), licensed MIT. It adds 8,005 tokens to every session, about $0.0400 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

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

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