ynab-mcp-server: Instructions file for Claude Code

CLAUDE.md

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

Project instructions for a local YNAB MCP server, including its architecture, data models, API connection, and handling of access tokens.

In plain words
What is it for?
They are for guiding development of YNAB budget and transaction tools, including API changes and secure token handling.
Why use it?
They help agents understand the codebase and avoid exposing sensitive financial credentials.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wgdevelopment/ynab-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/wgdevelopment/ynab-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 5.5 $0.00364 $0.00364
Sonnet 5.5 $0.00182 $0.00182
Haiku 4.5 $0.00091 $0.00091

Measured 2mo ago against content hash 1af74b71e417, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ynab-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 2mo 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 · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YNAB MCP Server - Claude Code Context

Project Overview

A minimal, auditable MCP (Model Context Protocol) server for YNAB budget management. Designed for local AI assistants that need to read and modify YNAB budgets while keeping sensitive financial context local.

Architecture

src/ynab_mcp_server/
  __init__.py     # Package initialization
  api.py          # YNAB API client (~300 lines, all network communication)
  models.py       # Pydantic models for YNAB data structures
  server.py       # MCP server implementation with tool handlers

Key Components

  • api.py: All YNAB API communication goes through here. Single endpoint: https://api.ynab.com/v1
  • server.py: MCP tool definitions and handlers. Entry point via ynab-mcp run
  • models.py: Type-safe Pydantic models for budgets, accounts, categories, transactions

Security Considerations

Token Handling

  • YNAB Personal Access Token stored in OS keyring (recommended) or environment variable
  • Token retrieved at runtime via keyring library or YNAB_API_TOKEN env var
  • NEVER log tokens - audit api.py for any logging statements

Data Flow

  • Local: User goals, AI coaching responses, conversation history, life context
  • To YNAB API: Only structured API calls (get categories, create transaction, etc.)

Audit Points

When reviewing changes, check:

  1. api.py - All network calls, ensure no token leakage
  2. Error handlers - Should not expose sensitive data
  3. Logging statements - Should not include tokens or financial details

Development

Setup

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows

# Install with dev dependencies
pip install -e .[dev]

Testing

pytest -v
pytest --cov=src/ynab_mcp_server  # with coverage

Linting

pip install ruff
ruff check src/
ruff format src/

CI/CD

Comprehensive quality gates run on all PRs:

  1. Tests: Python 3.10, 3.11, 3.12 matrix with coverage
  2. Semgrep: SAST scanning (security-audit, OWASP, Python, secrets)
  3. pip-audit: Dependency vulnerability scanning
  4. Linting: Ruff + Super-Linter (YAML, Markdown, Shell)
  5. Type Checking: mypy
  6. Claude Review: AI code review after all gates pass

Read the full file on GitHub · 110 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. 2mo ago First seen · 110 lines · 911 tokens per session scan A 1af74b71e417

Subscribe to this mod's changes

ynab-mcp-server CLAUDE.md is an instructions file published in the GitHub repository WGDevelopment/ynab-mcp-server (0 stars, last pushed 9mo ago), licensed MIT. It adds 911 tokens to every session, about $0.0036 per session on Opus 5.5. 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 2026-09-01.

Related

ynab-mcp-server CLAUDE.md compared with instructions from other repositories

ynab-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ynab-mcp-server CLAUDE.mdWGDevelopment/ynab-mcp-serverInstructions file09mo agoMITA911Claude 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 file150kyesterdayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283kyesterdayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot