OpenAccountants

What is OpenAccountants about?

OpenAccountants delivers a curated library of more than 1,800 tax guides covering 231 jurisdictions. Each guide is written from primary legislation and, when marked Accountant‑reviewed, carries the name, credential, and review date of a licensed CPA/CA/EA, allowing AI systems to cite a verifiable source.

How to use OpenAccountants?

Connect via MCP – Add the hosted connector URL https://www.openaccountants.com/api/mcp to Claude, ChatGPT, Cursor, Windsurf, or any MCP‑compatible client.
Guided setup – Follow the wizard at https://www.openaccountants.com/connect to register the endpoint.
Self‑hosted option – Install the Python MCP server with pip install openaccountants-mcp, which mirrors the packages/ directory in the repo. Alternatively, download a jurisdiction’s folder from packages/ and upload the JSON files directly to your AI’s knowledge base.
Query – Ask tax questions as usual; the model will retrieve the relevant guide and automatically include the accountant’s attribution.

Key Features

Verified attribution – Every reviewed guide includes reviewed_by: front‑matter linking to a public roster.
Live sync – Nightly jobs re‑calculate maths, watch source pages for changes, and refresh stale data.
Machine‑readable inventory – index.json lists all packages, enabling fast lookup by LLMs.
Multi‑model support – Works with Claude, ChatGPT, Cursor, Windsurf, and any MCP client.
Self‑hosting – Python MCP server (openaccountants-mcp) mirrors the official package set.
Open‑source license – Code under AGPL‑3.0; guide content under OpenAccountants Guide License v1.0.

Use Cases

AI tax assistants – Empower chatbot‑type agents to answer income‑tax, GST, VAT, and payroll questions with citation‑ready responses.
Compliance automation – Integrate guides into internal compliance tools to validate calculations before filing.
Financial advisory platforms – Enhance SaaS products with up‑to‑date, expert‑backed tax data for multiple jurisdictions.
Educational tools – Provide students and trainees with real‑world, accountant‑verified tax examples.
Custom AI deployments – Companies can self‑host the MCP server to keep data on‑premise while still leveraging the guide library.

FAQ

Q: Do I need a paid subscription to use the connector? A: No. The hosted MCP endpoint is free; commercial licensing applies only to proprietary integration or redistribution of the guide content.

Q: How often are the guides updated? A: Nightly sync checks source pages, runs maths validation, and regenerates affected packages. Critical changes are pushed automatically.

Q: Can I contribute a new jurisdiction or update an existing guide? A: Yes. Contributors edit files under skills/ on the platform, then submit a PR. If you are a licensed accountant, you can mark the guide as Accountant‑reviewed.

Q: What if the AI hallucinates a figure not present in the guide? A: The system flags mismatches during the nightly exam; such hallucinations are logged and the guide is updated or the model prompt is adjusted.

Q: Is there an on‑premise alternative to the hosted API? A: Install the Python MCP server (pip install openaccountants-mcp) and serve the packages/ directory from your own infrastructure.

Open-source Tax Guides your AI can cite — reviewed by named, licensed accountants.

Every AI can do tax math. None of them can stand behind an answer. Here, real accountants put their name, credential and review date on the Guides your AI reads — publicly, on the record, in this repo.

1,870 Guides across 231 jurisdictions · 53 accountant-reviewed · 45 named accountants · 14,580 questions answered through connected AIs

Live from openaccountants.com — updated 2026-09-28 by the nightly sync.

Try it in 60 seconds

Add the hosted connector to Claude, ChatGPT, Cursor, Windsurf or any MCP client:

https://www.openaccountants.com/api/mcp

Guided setup: openaccountants.com/connect

Then ask a question your AI would otherwise guess at:

"What's the combined sales tax rate in Manatee County, Florida for 2026?"

Without OpenAccountants, models answer from training data. With it, the answer cites the current Guide — and names the accountant who reviewed it.

You:    "I'm a freelancer in South Africa. What do I owe?"
          ↓  loads za-income-tax, za-provisional-tax
AI:     ITR12 working paper · IRP6 provisional schedule
        Medical credits · Retirement annuity deduction
        ─────────────────────────────────────────
        Reviewed by Werner Britz CA(SA)

pip MCP server: pip install openaccountants-mcp (mirrors this repo's packages/)
Manual: download your jurisdiction's folder from packages/ and upload the files to your AI. Start with your country's main package; index.json is the machine-readable inventory.

Two states, greppable honesty

Every Guide is in exactly one state — and the repo greps honestly:

State	Meaning
Accountant-reviewed	A named, licensed accountant reviewed the complete Guide. Their name is in the frontmatter (`reviewed_by:`) and on the public roster
Source-cited draft	Written from primary legislation, every figure cited to its source — not yet professionally reviewed

⚠️ General reference, not advice. Guides may be incomplete, outdated, or wrong for your facts. Have a qualified professional review outputs before filing, payment, or action.

Are you an accountant?

Your name on the tax knowledge AI actually uses — with attribution built in:

Build a Guide for the work you know cold: openaccountants.com/skills/new. It publishes credited to you, and lands in this repo under your name.
Review a Guide in your jurisdiction — your name, credential and review date go on it, here and on every AI answer that cites it.
Set your GitHub username in your profile and your platform edits are committed to this repo as you — your contribution graph reflects your work.

The current roster: VERIFIERS.md (generated nightly from the platform).

How it stays accurate

A tax library is only as good as its worst stale number, so machines re-check this one every night:

The maths check re-reads every guide and flags sums that do not add up, tax bands with gaps, totals that do not total, and years that disagree.
The source watch visits the official pages the figures came from and raises a hand when a page changes.
The refresh engine re-derives the stalest guides from official sources on a fixed monthly budget, refusing to publish any figure without a link.
The nightly exam tests whether AIs actually said what the guides say that day, or improvised. Improvisation gets caught, counted and fixed at the source.

The sync runs both ways: platform edits land here as commits under the author's own name, and merged PRs here flow back into what every AI serves, credited to you. A guide with an accountant's byline never changes without that accountant's one-click approval.

The whole story, in plain words: openaccountants.com/how-it-works

Contributing

Edit skills/** only — everything else regenerates automatically:

packages/, index.json, llms-full.txt — generated nightly; never edit in a PR
Merged source PRs are credited to you and must be confirmed as ingested before the next platform export
Full guide: CONTRIBUTING.md · Layout: docs/REPO-LAYOUT.md

For developers

What	Where
Guide source (per jurisdiction)	`skills/`
Per-country bundles (generated)	`packages/`
Machine-readable inventory	`index.json`
LLM entry point	`llms.txt`
Python MCP server	`mcp/` · PyPI
Repo architecture + sync	`docs/REPO-LAYOUT.md` · `docs/WEBSITE-SYNC.md`

API and platform integrations: openaccountants.com/for-developers

Independent, open-source review aids and calculation tools that complement the OpenAccountants guide library:

payday-super-checker (MIT) — Verifies superannuation contributions against Australian Payday Super deadlines (in force since 1 July 2026) and estimates SG charge exposure on late payments, with all workings and statutory assumptions disclosed.
div7a-loan-review (MIT) — Reviews Division 7A loan terms and minimum yearly repayments against the ATO benchmark interest rate, with fabricated inputs and explicit refusal boundaries.
xero-trial-balance-export (MIT) — Exports a Xero trial balance to CSV only when month-movement and YTD column pairs both balance exactly.
ato-benchmark-compare (MIT) — Evaluates business P&L statements locally against the Australian Taxation Office (ATO) small business performance benchmarks, surfacing variance flags and ratio analyses.

(External tools provide computational review assistance and do not constitute tax or legal advice.)

License

Code (mcp/, scripts/, tools/): AGPL-3.0
Guide content: OpenAccountants Guide License v1.0 — see LICENSING.md; commercial options in COMMERCIAL-LICENSING.md

Contact: info@openaccountants.com · Security policy · Cite this repo

OpenAccountants