Sumsub has launched a Model Context Protocol (MCP) integration and a suite of AI agent skills designed to let compliance teams use large language model-based agents to configure and manage verification workflows.
The new capability allows teams to upload anti-money laundering (AML) policies or regulatory requirements to AI agents such as Claude, ChatGPT or other leading models, and use those agents to generate Sumsub workflow configurations directly from the source document. In practice, that means country-specific risk brackets, weighted scoring tables and conditional onboarding logic can be translated into verification levels, risk questionnaires and onboarding workflows inside the customer’s Sumsub dashboard.
The development addresses one of the more time-consuming parts of compliance technology implementation: translating policy and regulatory requirements into operational settings. Traditionally, that work has required solution architects or technical teams to interpret AML policies, map requirements to platform controls and build onboarding workflows manually. Sumsub says a setup that previously could take days can now be completed in minutes.
The release also extends agentic functionality beyond workflow setup. AI agents can be used to support technical integration, including writing code to embed Sumsub verification into a customer onboarding flow. Day-to-day use cases include reviewing applicants, running analytics, generating verification links and responding to regulatory changes.
“Setting up a compliance workflow has always required significant manual effort, and updating it when regulations change requires even more,” said Andrew Novoselsky, Chief Product Officer at Sumsub. “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.”
The integration is model-agnostic and is designed to work with leading AI agents. Sumsub has also published an open-source set of agent skills on GitHub, which can be installed with a single terminal command.
The MCP integration builds on Sumsub’s broader AI strategy, including Summy, its AI Copilot for compliance and fraud teams inside the platform. Sumsub is positioning the release as part of a shift toward compliance infrastructure that can operate alongside the AI tools and workflows used by operational, compliance and technical teams.
Sumsub says access to the MCP integration is controlled through separate permissions to support granular data governance. Sensitive actions are performed in an isolated sandbox, with configuration changes reviewed and approved by a human before being applied.
The integration is available now. Sumsub says it is the first verification platform to be officially listed on the ChatGPT Apps platform, with further discussions ongoing with additional large language model providers. Documentation and agent skills are available through Sumsub’s developer resources.
Subscribe to our newsletter
