Sumsub has become the first provider in its space to give AI agents the ability to configure and build out an entire compliance environment through a new Model Context Protocol (MCP) integration and accompanying suite of AI agent skills.
The new capabilities allow AI agents, including Claude, ChatGPT and other leading models, to take a compliance policy document and translate it directly into a fully operational platform setup. Where previously a complex AML policy containing country-specific risk brackets, weighted scoring tables and conditional logic would need to be interpreted and manually configured by technical teams, the AI agent can now read that document and produce live platform settings, covering verification levels, risk questionnaires and onboarding workflows, directly in the customer's dashboard. A process that once required days can now be completed in minutes.
The release introduces three core capabilities. Teams can upload their AML policy or regulatory requirements and instruct an AI agent to configure their Sumsub environment accordingly. Separately, AI agents can handle the technical side of embedding Sumsub into a client's application by writing the necessary code and building verification into the onboarding flow in real time. Ongoing compliance management is also supported, with agents able to review applicants, run analytics, generate verification links and adapt to regulatory changes as they occur.
Sumsub is a full-cycle verification platform built to support fraud-free, scalable compliance. Its existing product set includes Summy, an AI copilot designed for use by compliance and fraud teams within the platform itself.
The MCP integration is model-agnostic and compatible with any leading AI agent. Sumsub has published an open-source collection of agent skills on GitHub, installable via a single terminal command. Access to the integration is governed by separate permissions to allow granular data control. Sensitive actions are carried out in an isolated sandbox environment, ensuring that any configuration changes are reviewed and approved by a human before taking effect.
Sumsub chief product officer Andrew Novoselsky said, 'Setting up a compliance workflow has always required significant manual effort, and updating it when regulations change requires even more. Our Agentic experience changes that by connecting an AI agent directly to the configuration layer of the platform - a team can take their AML policy, hand it to an AI agent, and have their full environment built automatically. That is a fundamentally different category of capability from what has been available in this space.'