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.
curl -O https://raw.githubusercontent.com/rjpaganini/quickbooks-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/rjpaganini/quickbooks-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/rjpaganini/quickbooks-mcp-server/claude-md)<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.
<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>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 5.5 | $0.00668 | $0.00668 |
| Sonnet 5.5 | $0.00334 | $0.00334 |
| Haiku 4.5 | $0.00167 | $0.00167 |
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 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.
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,
FastMCPinstance - 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.toolfunctions 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(wasqbo_company_info) and_list_transactions_all(wasqbo_list_transactions). - v2.0.0 Dispatcher Tools: 8 new
@mcp.toolfunctions consolidating the surface. See## v2.0.0 Tool Surfacebelow. - Entry Point:
mcp.run()(stdio default,--remotefor streamable-http)
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 · 100 lines · 1,669 tokens per session scan A a6fe09d50f22
quickbooks-mcp-server CLAUDE.md is an instructions file published in the GitHub repository rjpaganini/quickbooks-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,669 tokens to every session, about $0.0067 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.
quickbooks-mcp-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| quickbooks-mcp-server CLAUDE.mdrjpaganini/quickbooks-mcp-server | Instructions file | 0 | 2mo ago | MIT | A | 1,669 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | yesterday | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |