Frontier models reason brilliantly but guess on regulation, hallucinated citations, stale texts, no way to tell a draft from law in force. Obsidian is the verified, tier-0 regulatory data layer they call. Connect it to Claude, ChatGPT, or Cursor in two minutes and turn confident guesses into cited, current, verifiable answers.
Works with the assistants you already use
Claude
ChatGPT
Cursor
Perplexity
Grok
Ever been let down by your AI on a regulatory question?
You ask. It answers, fast, fluent, completely confident. But you can't quite trust it: the citation might not exist, the text might be months out of date, and it can't tell a draft from a regulation in force.
It's not the model's fault. It simply doesn't have the data. Frontier models are brilliant reasoners with no structured, verified regulatory database to stand on.
That's exactly what Obsidian brings.
You already have the intelligence. We bring the data.
850+ official sources · 50+ jurisdictions · every record double-checked
The missing layer
The bottleneck for agentic regulatory work was never intelligence, it was ground truth. Here is the exact same prompt, with and without the Obsidian MCP connected.
"Based on my training data, the EU is working on a broad PFAS restriction under REACH. A consultation was expected, and restrictions may phase in over the coming years…"
Cites a regulation number that may not exist. No date. No link."ECHA opened a consultation on the PFHxA derogations on 2026-05-04 (status: open, closes in 60 days). The universal PFAS restriction dossier remains under committee review at RAC/SEAC."
The logic
Everyone now works through an AI assistant. You ask it a regulatory question.
You get a fluent, confident answer in seconds.
But is it true? Is it current? Is the citation real?
Models are trained on stale, unverified web text. On regulation they hallucinate.
In compliance, "probably right" is a liability. A wrong answer has a cost.
The fix isn't a smarter model, it's a verified source of truth it can call. An MCP server.
Obsidian is that server. Tier-0 official sources, double-checked, versioned, global coverage. Connect it in two minutes, free.
Why it's the best regulatory MCP
Straight from regulators, official journals, and agencies, EUR-Lex, ECHA, FDA, EFRAG, and hundreds more. Not a scrape of the open web.
Every record is parsed, deduplicated, validated, and provenance-stamped. If we surface it, it traces back to an official document.
Know exactly when something changed, and whether it's a draft, in consultation, adopted, or in force. The distinction your assistant can't guess.
50+ jurisdictions across Chemicals, ESG, and Life Sciences, expanding continuously. One connection, worldwide reach.
Every answer returns a source, date, jurisdiction, framework, and relevance score, so your assistant cites instead of inventing.
Claude, ChatGPT, Cursor, Perplexity, any MCP-compliant client. Two-minute setup, generous free tier, no lock-in.
Pricing
Start free. Scale when your agents do. Same logic as your AI subscription, simpler to reason about.
A "verified request" is one answered call to the MCP, returned with sources. Early access: join the waitlist to lock in founder pricing.
Early access
We're rolling out the Obsidian MCP to early users now. Join the waitlist and we'll send your key, founder pricing, and the two-minute setup guide.
FAQ
It's an MCP (Model Context Protocol) server that gives your AI assistant a verified, tier-0 regulatory data layer. Instead of answering from memory, your assistant calls Obsidian and returns regulatory information sourced straight from official regulators, journals, and agencies, with dates, status, and links.
Any MCP-compliant client. That includes Claude (desktop and Claude Code), Cursor, and a growing list of assistants and IDEs. ChatGPT, Perplexity, and Grok are supported as the MCP ecosystem rolls out across them. If your tool speaks MCP, Obsidian plugs in.
Yes. The free tier gives you 100 verified requests per month, one seat, and no credit card. It's meant for real use, not a trial that expires. Paid tiers simply raise the monthly request allowance and unlock all frameworks and jurisdictions.
From tier-0 official sources only: regulators, official journals, standard-setters, and agencies such as EUR-Lex, ECHA, the FDA, and EFRAG, hundreds of official sources across 50+ jurisdictions. Every record is parsed, deduplicated, validated, and provenance-stamped before it can be returned.
Asked directly, a model answers from training data: it can be outdated, can't cite a verifiable source, and can't tell a draft from a regulation in force. With Obsidian connected, the same model answers from live, official, double-checked data, with the source, the date, and the link. Confident guesses become defensible answers.
Join the waitlist to get your free API key, then paste one configuration block into Claude, Cursor, or your MCP client, about two minutes. From then on you just ask in plain English and your assistant does the rest.
