ATO MCP

Add the MCP Server to the client you already use.

Standard configworks with most tools that run stdio servers:

Everything the ATO publishes, in one searchable place, refreshed monthly:

34,500+ documents (286,000+ searchable passages), refreshed monthly and served from the hosted platform.

"Here's my bank transactions, what can I claim this year? How do I write off my new laptop? Is anything in my return risky?"

Every workflow tool returnsstructured data and resolvable ATO citations, never advice in its own voice.

Personal context:get_user_facts, 25 facts captured once at onboarding (business structure, GST registration, investments, super type, residency, …) so the agent never re-asks.

Retrieval:search(keyword and semantic retrieval),get_chunks,get_doc,get_doc_anchors(cross-references),get_definition(statutory, point-in-time),get_threshold(time-keyed values),fetch(live page fetch),stats.

This service is provided asinformation infrastructure, not tax advice. It does not consider your full financial circumstances and it is not a registered tax agent service. Confidence ratings and risk bands are guides, not professional judgement. Verify material decisions with a registered tax agent.

ato-mcp is an independent service. It is not affiliated with or endorsed by the Australian Taxation Office. ATO content remains subject to ATO publication terms. Legislation text is reproduced from the Federal Register of Legislation under its open licensing.

The hosted platform and corpus are proprietary. Commercial licensing available on request.

Agent-to-agent knowledge exchange for trading intelligence — publish empirical findings, vote on quality, earn reputation, and unlock higher-credibility collective intelligence the more you contribute.

Remote MCP server giving AI assistants access to 20,000+ corporate KPI definitions, formulas, and 30,000+ source-attributed industry benchmarks.

Semantic search over 4.6M+ text chunks from 20,000+ classical philosophy and humanities works — Plato, Aristotle, Kant, Nietzsche, and thousands more. Multilingual (Greek, Latin, German, French, English). No install needed.

Multimodal RAG for source-backed AI answers

An MCP server for interacting with Dappier's Retrieval-Augmented Generation (RAG) models.

Source-grounded MCP, A2A, and x402 metadata for verified knowledge commerce.

A free, plug-and-play knowledge base with over 10,000 built-in insight reports and support for parsing private documents.

A lightweight Python server for Retrieval-Augmented Generation (RAG) using AWS Lambda. It retrieves knowledge from external data sources like arXiv and PubMed.

A private, local research "second brain" for Claude — cited answers from your own library (it won't invent what it can't find), persistent project memory, daily briefs, a live meeting assistant, and 34 specialist agents. Runs entirely on your machine.