An astronaut overseeing a futuristic data hub

Connect OpenSanctions to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Verify entities against global sanctions and PEP lists instantly.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 8 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 8 available through OpenSanctions.

  1. 01

    Match pep

    Screens names against Politically Exposed Persons lists. It returns match scores, matched entities, and specific political positions for KYC/AML checks.

  2. 02

    Search entities

    Searches the database for sanctioned persons, companies, or vessels. You can use the schema parameter to filter results by specific entity types.

  3. 03

    Search person

    Finds individuals within the sanctions database. It provides names, aliases, birth dates, and nationality information.

  4. 04

    Search vessel

    Identifies sanctioned ships by name or IMO number. It returns details on flags, owners, and current sanctions status.

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through OpenSanctions.

  1. 05

    Get datasets

    Lists all available sanctions datasets. It shows dataset names, descriptions, and the number of entities in each.

  2. 06

    Get entity

    Retrieves deep profile information for a specific entity ID. This includes addresses, related entities, and full sanctions history.

  3. 07

    Match sanctions

    Performs fuzzy matching against global sanctions lists. You can adjust the sensitivity using a threshold parameter from 0.0 to 1.0.

  4. 08

    Search company

    Locates sanctioned businesses. It returns registration numbers, jurisdictions, and addresses.

Real work

What teams actually run

01

Customer Onboarding

Run a quick check on a new user to see if they appear on any PEP or sanctions lists.

02

Supply Chain Risk

Verify that shipping vessels or logistics companies are not flagged by international regulators.

03

Corporate Due Diligence

Investigate company registration numbers and jurisdictions to find hidden sanctions links.

04

Regulatory Research

Query specific datasets to understand the scope of different global sanctions regimes.

Automate a task

Put OpenSanctions to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

OpenSanctions works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put OpenSanctions to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

954ms average. Fast in production.

OpenSanctions is checked daily against the live service.

Daily averagePeak 1104ms
Oct 3Today
Fastest day
721ms
Slowest day
1104ms
14-day trend
Slowing+8%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 8 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of OpenSanctions, so you can see the experience inside your AI.

It does not authenticate your account with OpenSanctions. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

OpenSanctions Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_ZsvZF1zehQBkE9Qy8D6NL3kDsgqsOFIaEJphQI9f/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — OpenSanctions capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "opensanctions-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_ZsvZF1zehQBkE9Qy8D6NL3kDsgqsOFIaEJphQI9f/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up OpenSanctions in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work OpenSanctions owners hand off.

This MCP is built for professionals who need to verify identities and organizations against regulatory lists without leaving their primary workspace.

  • 01

    Compliance Officers

    They use the agent to screen clients and partners against global lists.

  • 02

    Financial Institutions

    They run KYC and AML checks on customers and transactions.

  • 03

    Researchers

    They explore entity relationships and PEP database connections.

FAQ

Questions OpenSanctions owners ask.

  • 01

    Do I need an API key to use this?

    No API key is required for non-commercial use.

  • 02

    Which sanctions lists are included?

    The data includes OFAC, EU, UN, UK HMT, and over 40 other global sanctions regimes.

  • 03

    Can I search for ships?

    Yes, you can search for sanctioned vessels by name or IMO number.

  • 04

    How accurate is the matching?

    The MCP uses fuzzy matching and allows you to adjust the sensitivity using a threshold parameter.

  • 05

    What kind of entity info can I get?

    You can get names, aliases, dates of birth, nationalities, addresses, and sanctions status.

  • 06

    Do I need an API key?

    No! OpenSanctions is completely free for non-commercial use. No authentication required.

  • 07

    What sanctions lists are included?

    OpenSanctions aggregates data from OFAC (US), EU Consolidated List, UN Security Council, UK HMT, and many other global sanctions regimes.

  • 08

    How accurate is the name matching?

    The API uses fuzzy matching with configurable thresholds (0.0-1.0). Default threshold of 0.85 balances accuracy and recall for most use cases.

  • 09

    Can I screen companies, not just individuals?

    Yes! Use search_company to find sanctioned companies, or use the general search with schema='Company' filter.

Connect OpenSanctions to Claude, Cursor, ChatGPT & more