What is ledgerlink-mcp CLAUDE.md?

Developer instructions for LedgerLink MCP, a service that connects AI assistants to QuickBooks Online. It covers managing invoices, customers, expenses, reports, and other accounting records.

Guiding development of QuickBooks operations, OAuth login, MCP tools and resources, rate limiting, queries, and report formatting.

It explains the project’s current state, architecture, authentication, API handling, and development priorities for agents working on the code.

How bpmj-martin/ledgerlink-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bpmj-martin/ledgerlink-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/bpmj-martin/ledgerlink-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/bpmj-martin/ledgerlink-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bpmj-martin/ledgerlink-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/bpmj-martin/ledgerlink-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bpmj-martin/ledgerlink-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bpmj-martin/ledgerlink-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bpmj-martin/ledgerlink-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bpmj-martin/ledgerlink-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 696 This file is loaded in full into every session.

When invoked 696 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.

Model	Per session	Once invoked
Fable 5.1	$0.00696	$0.00696
Opus 5.5	$0.00278	$0.00278
Sonnet 5.5	$0.00139	$0.00139
Haiku 4.5	$0.00070	$0.00070

Measured 2mo ago against content hash da60b480acae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ledgerlink-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 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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project: LedgerLink MCP

Overview

MCP server for QuickBooks Online — lets AI assistants manage invoices, customers, expenses, and reports via natural language. 32 tools across 10 entities, 5 read-only resources.

Current State

Status: In Progress
Last session: 2026-02-17
Working on: Core build complete (Steps 3-6). Next: QB dev account setup, then test with MCP Inspector + Claude Desktop.

Recent Changes

2026-02-17: Project scaffolded — package.json, tsconfig, tsup, directory structure, git init, deps installed
2026-02-17: Built full MCP server — OAuth flow, QB client with rate limiting, 32 tools, 5 resources, CLI auth command. TypeScript compiles clean, tsup build succeeds.

Architecture

Entry point: src/index.ts (MCP server) + bin/cli.ts (CLI for auth)
Key modules:
- src/auth/ — OAuth 2.0 flow + token storage (~/.ledgerlink/)
- src/quickbooks/ — QB API client + entity operations (10 files)
- src/tools/ — MCP tool registrations (10 files, 32 tools total)
- src/resources/ — 5 MCP resources (company, accounts, customers, vendors, items)
- src/utils/ — Rate limiter (450 req/min), query builder with sanitization, report formatter
External deps: @modelcontextprotocol/sdk, zod, open
Transport: stdio (Claude Desktop) + Streamable HTTP (future hosted)

Tech Stack

TypeScript 5.x / Node.js 24
MCP SDK (@modelcontextprotocol/sdk) — imports from sdk/server/mcp.js and sdk/server/stdio.js
Zod for schema validation
QuickBooks Online REST API v3

Build Steps (from SPEC.md)

Step 1: Environment setup
Step 2: Project scaffolding
Step 3: Basic MCP server skeleton
Step 4: OAuth 2.0 integration
Step 5: First real tool (invoices)
Step 6: All remaining tools (32 total)
Step 7: Test with MCP Inspector (needs QB dev account)
Step 8: Test with Claude Desktop
Step 9: Error handling hardening
Step 10: Packaging for distribution (npm publish)
Step 11: MCP marketplace listings (Smithery, etc.)

Read the full file on GitHub · 61 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.

2mo ago First seen · 61 lines · 696 tokens per session scan A da60b480acae

Subscribe to this mod's changes

ledgerlink-mcp CLAUDE.md is an instructions file published in the GitHub repository bpmj-martin/ledgerlink-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 696 tokens to every session, about $0.0028 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 2026-08-31.

Finance and fintech accounting ai mcp-server model-context-protocol quickbooks

ledgerlink-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ledgerlink-mcp CLAUDE.mdbpmj-martin/ledgerlink-mcp	Instructions file	0	8mo ago	MIT	A	696	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

ledgerlink-mcp: Instructions file for Claude Code