openaccountants-mcp

OpenAccountants

Open tax skills for AI. Your AI answers tax questions from memory. Add these skills and it answers from the law: every rate, threshold and deadline cited to its official source, for 266 jurisdictions.

2,105 AI skills across 253 jurisdictions · 33 accountant-reviewed · 39 named accountants · 22,112 questions answered through connected AIs

_{Live from openaccountants.com — updated 2026-10-27 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

Listed on Smithery and the MCP Registry.

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 can cite the fetched skill and its review status. Name a professional reviewer only when that skill version has a published review record.

You:    "I'm moving to Malta and selling my company next year. What tax do I face?"
          ↓  loads moving-to-malta-tax-residence, selling-a-company-in-malta
AI:     Residence and domicile · Remittance basis on foreign income
        Gain on the share sale · Participation exemption check
        ─────────────────────────────────────────
        Authored by Michael Cutajar CPA, ACCA (Malta)

Prefer self-hosting or manual files?

• 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.

---

Three states, greppable honesty

This library holds accountant-reviewed skills and skills no accountant has signed off yet. Check each skill version's review record before relying on it; a named author is distinct from a professional reviewer. Skill content is source-available under the terms in LICENSING.md.

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

State	Meaning
Accountant-reviewed	A named, licensed accountant reviewed the complete skill. Their name is in the frontmatter (reviewed_by:) and on the public roster
Checked against the law	Built to the standard in docs/skill-template.md: every figure cited to the law and checked against the statute by an independent review before merge; no accountant has signed it off yet
Sourced from the law	Older skill not yet rebuilt to the standard: every figure cited to an official source; no accountant has signed it off yet

The definitions: docs/QUALITY-TIERS.md. How skills are built, checked and corrected: docs/ACCURACY-METHODOLOGY.md. Which number to quote and where it is measured: docs/COVERAGE.md.

⚠️ General reference, not advice. Skills 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:

1. Build a skill for the work you know cold: openaccountants.com/skills/new. It publishes credited to you, and lands in this repo under your name.
2. Review a skill in your jurisdiction — your name, credential and review date go on it, here and on every AI answer that cites it.
3. 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).

---

Need the work done?

OpenAccountants also does the bookkeeping, VAT, payroll and tax work for businesses, in the countries they work in. Talk to us. The skills and the AI connection stay free.

---

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 skill 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 skills 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 skills 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 skill 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

The goal is one complete, verified, reviewed tax pack per jurisdiction: GOAL.md. Who owns which jurisdiction: OWNERS.md. Take an open [XX] Complete the pack issue and open a PR with Closes #N.

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

• packages/, agent-skills/<slug>/, 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 instructions: CONTRIBUTING.md · Layout: docs/REPO-LAYOUT.md

---

For developers

What	Where
Skill 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

---

Related open-source projects

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

• payday-super-checker (Apache-2.0) — 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 (Apache-2.0) — 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 (Apache-2.0) — Exports a Xero trial balance to CSV only when month-movement and YTD column pairs both balance exactly.
• ato-benchmark-compare (Apache-2.0) — 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/, calculators/): AGPL-3.0-only
• Skill content: OpenAccountants Guide License v1.0 — see LICENSING.md; commercial options in COMMERCIAL-LICENSING.md

Contact: [email protected] · Security policy · Cite this repo