Obsidian Regulatory MCP

Customer support

Pricing Press

Dev

MCP Documentation

| Login| Register

Model Context Protocol · Free tier

The regulatory layer for your AI.

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.

Create your free account See the difference

No credit card 75 free requests / month Tier-0 official sources

Works with the assistants you already use

Claude ChatGPT Cursor Perplexity Grok

Add it to Claude, Cursor, or any MCP client

claude mcp add --transport http obsidian-regulatory https://mcp.obsidianri.com/mcp Copy

Claude, ChatGPT, Cursor & more: add the endpointhttps://mcp.obsidianri.com/mcp as a custom connector. The free tier works instantly, no API key.

Step-by-step guides with screenshots, for 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 But you can't quite trust it: the citation might not exist, the text might be months out of date, and it can't tell a draft from a regulation in force.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.

900+ official sources · 50+ jurisdictions · every record double-checked

The missing layer

Same model. Same question. One source of truth.

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.

What's the latest on the EU PFAS restriction?

"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.

• Possibly outdated, training cut-off

• Unverifiable citation

• Draft or in force? Unknown

vs

"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."

ECHA 2026-05-04 EU source

• Tier-0 official source (ECHA)

• Dated & versioned

• Double-checked, link included

The logic

Why a regulatory MCP is inevitable.

01

Everyone now works through an AI assistant. You ask it a regulatory question.

02

You get a fluent, confident answer in seconds.

03

But is it true? Is it current? Is the citation real?

04

Models are trained on stale, unverified web text. On regulation they hallucinate.

05

In compliance, "probably right" is a liability. A wrong answer has a cost.

06

The fix isn't a smarter model, it's a verified source of truth it can call. An MCP server.

07

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

Built for answers you can defend.

Tier-0 official sources

Straight from regulators, official journals, and agencies, EUR-Lex, ECHA, FDA, EFRAG, and hundreds more. Not a scrape of the open web.

Double-checked

Every record is parsed, deduplicated, validated, and provenance-stamped. If we surface it, it traces back to an official document.

Dated & versioned

Know exactly when something changed, and whether it's a draft, in consultation, adopted, or in force. The distinction your assistant can't guess.

Global coverage

50+ jurisdictions across Chemicals, ESG, and Life Sciences, expanding continuously. One connection, worldwide reach.

Structured & cited

Every answer returns a source, date, jurisdiction, framework, and relevance score, so your assistant cites instead of inventing.

Works with your stack

Claude, ChatGPT, Cursor, Perplexity, any MCP-compliant client. Two-minute setup, generous free tier, no lock-in.

Pricing

One subscription, MCP included

Your MCP access, the AI assistant, monitoring and the full platform run on one plan and one monthly credit. Start free, scale when your agents do.

Free

Occasional use

$0/mo

Try now

Free forever · no card required

• 1 jurisdiction

• $3 / mo in usage credit

• 75 verified lookups / mo

• AI chat assistant

Pro

Regular use

$20/mo

or $200 / year, save 17%

Try now

7-day free trial · cancel anytime

• 3 jurisdictions

• Everything in Free, plus

• $20 / mo in usage credit

• 500 verified lookups / mo

• 3 monitoring jobs weekly

• MCP for AI agents

Expert 5x

Frequent users across a variety of tasks

$100/mo

Try now

• 10 jurisdictions

• Everything in Pro, plus

• $100 / mo in usage credit

• 2,500 verified lookups / mo

• 20 monitoring jobs daily

• API access + news feed

Expert 20x

Daily power users who collaborate often

$200/mo

Try now

• All jurisdictions

• Everything in Expert 5x, plus

• $200 / mo in usage credit

• 5,000 verified lookups / mo

• 100 monitoring jobs hourly

• Full app access

Pro$20 / mo Expert 5x$100 / mo Expert 20x$200 / mo CoverageJurisdictions in your regulatory perimeter. Jurisdictions covered 3 10 All AI assistantClaude, Gemini and GPT, grounded in live regulation. Monthly usage credit $20 $100 $200 All models (Claude, Gemini, GPT) Verified regulatory lookups / mo 500 2,500 5,000 Grounded answers, with sources & dates Conversation history & saved chats MonitoringAlways-on watchers that alert you the moment a rule changes. Monitoring jobs 3 20 100 Check frequency Weekly Daily Hourly Alert channels Email, Push, Slack Email, Push, Slack, WhatsApp Email, Push, Slack, WhatsApp, Teams Custom triggers & schedules Editable, reusable routines Web app & APIThe full regulatory dashboard and programmatic access. Regulatory dashboard REST API + MCP automation Single sign-on (Google & Microsoft) Team members & roles

Every plan draws from one monthly credit you spend across AI chat and verified regulatory lookups. Cancel or switch anytime. Just exploring? Create a free account, no card required.

A "verified request" is one answered call to the MCP, returned with sources. Every plan starts from a free account, no credit card, and upgrades whenever your agents need more.

Create your free account. Connect in two minutes.

No waitlist, no sales call. Register for a free Obsidian account and connect the MCP to Claude, ChatGPT, Cursor, or any MCP client right away. 75 verified requests a month, no credit card.

Create your free account Read the setup guide

Already have an account? Sign in. Free tier, no credit card. See our privacy policy.

FAQ

Questions, answered.

What is the Obsidian regulatory MCP?

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.

Which AI assistants does it work with?

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.

Is there really a free tier?

Yes. The free tier gives you 50 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.

Where does the regulatory data come from?

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.

How is this different from asking ChatGPT or Claude directly?

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.

How do I connect it?

Create a free account, 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. See the step-by-step setup guide.