What is quickbooks-mcp-server CLAUDE.md?

A server that lets Claude Code or Claude Desktop read and write QuickBooks Online data through its API, the interface provided by QuickBooks. It can run locally over standard input and output or remotely over HTTP.

Running a QuickBooks integration locally or remotely, accessing or changing QuickBooks Online records, and configuring production or sandbox accounts with environment variables.

It connects an AI coding assistant to accounting data while keeping the server's credentials and connection settings in one place.

How rjpaganini/quickbooks-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to rjpaganini/quickbooks-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/rjpaganini/quickbooks-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/rjpaganini/quickbooks-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/rjpaganini/quickbooks-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/rjpaganini/quickbooks-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/rjpaganini/quickbooks-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/rjpaganini/quickbooks-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.

Your own site · 80×15

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

Per session 1,669 This file is loaded in full into every session.

When invoked 1,669 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	$0.01669	$0.01669
Opus 5	$0.00834	$0.00834
Sonnet 5	$0.00334	$0.00334
Haiku 4.5	$0.00167	$0.00167

Measured 8d ago against content hash a6fe09d50f22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

quickbooks-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 · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

A single-file MCP (Model Context Protocol) server that provides Claude with read/write access to QuickBooks Online via the QBO API v3. Runs over stdio (Claude Desktop / Claude Code) and streamable-http (Pi deployment for mobile/web). Currently v2.0.0, see CHANGELOG.md for the consolidation from 45 → 22 tools landed 2026-05-11.

Running the Server

pip install mcp httpx python-dotenv
python server.py              # stdio (default, Claude Desktop / Code)
python server.py --remote     # streamable-http on :8809 (Pi deployment)

Requires a .env file with: QB_REALM_ID, QB_ACCESS_TOKEN, QB_REFRESH_TOKEN, QB_CLIENT_ID, QB_CLIENT_SECRET. Set QB_SANDBOX=true for sandbox mode (default: production realm).

Architecture

Everything lives in server.py (~2,800 lines). Key sections in order:

Module docstring: v2.0.0 + §5.5 session-profile block (per MCP-DESIGN-STANDARDS.md)
Config & Constants: OAuth credentials from env vars, in-memory token cache, FastMCP instance
Shared API Client: Core request helpers that all tools use:
- _qbo_request(), generic REST call with auto 401 retry
- _qbo_query(), QBO SQL-like queries (SELECT)
- _qbo_report(), report fetching (wraps _qbo_request)
- _refresh_access_token(), OAuth2 token refresh with Base64 client credentials
- _handle_error(), returns structured {error, status, hint, detail} envelopes per §3.5
- _parse_gl_rows(), parses GL report JSON into flat transaction lists (used by reconciliation tools)
Input Models: Pydantic models with validation. Original models (DateRangeInput, EntityIdInput, InvoiceCreateInput, etc.) + v2.0.0 dispatcher models (CompanyInfoInput, ListEntitiesInput, GetEntityInput, ListTransactionsInput, GetTransactionInput, GetReportInput, RunReconciliationInput)
Internal Helpers: 31 ex-@mcp.tool functions retained as plain async helpers, original names kept (qbo_list_customers, etc.) but no longer registered with FastMCP. Called by the v2.0.0 dispatchers. Two were renamed to avoid collision with new dispatcher tool names: _company_info_basic (was qbo_company_info) and _list_transactions_all (was qbo_list_transactions).
v2.0.0 Dispatcher Tools: 8 new @mcp.tool functions consolidating the surface. See ## v2.0.0 Tool Surface below.
Entry Point: mcp.run() (stdio default, --remote for streamable-http)

Read the full file on GitHub · 100 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.

8d ago First seen · 100 lines · 1,669 tokens per session scan A a6fe09d50f22

Subscribe to this mod's changes

quickbooks-mcp-server CLAUDE.md is an instructions file published in the GitHub repository rjpaganini/quickbooks-mcp-server (0 stars, last pushed 15d ago), licensed MIT. It adds 1,669 tokens to every session, about $0.0083 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.

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

quickbooks-mcp-server: Instructions file for Claude Code