Obsidian Regulatory MCP

Customer support|

Pricing News

Dev

MCP Documentation

| Login| Register| English

Model Context Protocol · Free tier

The regulatory layer for your AI.

Frontier models reason brilliantly but guess on regulation: invented citations, stale texts, no way to tell a draft from law in force. Obsidian is the verified, tier-0 data layer your AI calls for ground truth. Connect it to Claude, ChatGPT or Cursor in two minutes, and every answer comes back current, cited and checkable.

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 endpoint https://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 But you can't quite trust it: the citation might not exist, the text might be months out of date, and it can't tell a draft from a regulation in force.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.

4500+ official sources · 150+ 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 conversation, without and with the Obsidian MCP connected.

Without Obsidian

• Training data, months out of date
• Citation cannot be verified
• Draft or in force? It cannot tell

vs

With the Obsidian MCP verified

Same model, one connector added

• 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

150+ jurisdictions across every regulated industry we cover, 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.

Pro

Regular use

$20/mo

or $200 / year, save 17%

Try now

7-day free trial · cancel anytime

• 3 jurisdictions
• $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

• 5 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

• 10 jurisdictions
• Everything in Expert 5x, plus
• $200 / mo in usage credit
• 5,000 verified lookups / mo
• 100 monitoring jobs hourly
• Full app access

Enterprise

Organizations needing custom coverage, volume and terms

Custom

Contact sales

Custom terms · our team gets back within a day

• All jurisdictions
• Everything in Expert 20x, plus
• Custom usage credit & volume
• Unlimited monitoring jobs
• Full app + API access
• Dedicated support & onboarding

Pro$20 / mo	Expert 5x$100 / mo	Expert 20x$200 / mo	EnterpriseCustom
CoverageJurisdictions in your regulatory perimeter.
Jurisdictions covered	3	5	10	All
AI assistantClaude, Gemini and GPT, grounded in live regulation.
Monthly usage credit	$20	$100	$200	Custom
All models (Claude, Gemini, GPT)
Verified regulatory lookups / mo	500	2,500	5,000	Custom
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	Custom
Check frequency	Weekly	Daily	Hourly	Custom
Alert channels	Email, Push	Email, Push, Slack, WhatsApp	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: Claude (app, desktop and Claude Code), ChatGPT, Cursor, Perplexity, and a growing list of assistants and IDEs. If your tool speaks MCP, Obsidian plugs in.

Is there really a free tier?

Yes. The free tier gives you 75 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 150+ 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.