A setup that previously took solution architects days to complete now completes in a single step by handing a policy PDF directly to an AI agent.
Sumsub, a global verification and fraud prevention leader, today announced the launch of its Model Context Protocol (MCP) integration and a new suite of AI agent skills. This makes it the first identity verification and compliance platform to give AI agents, including Claude, ChatGPT, and other leading models, access not only to day-to-day operations but also to the full configuration and setup layer of the platform.
With Sumsub’s agentic experience, an AI agent can take a real compliance policy document and automatically generate a fully configured Sumsub environment. That means even a complex, multi-page PDF with country-specific risk brackets, weighted scoring tables, and conditional logic gets translated into live platform settings, including verification levels, risk questionnaires, and onboarding workflows, directly in the customer’s dashboard. A setup that previously could take days can now be completed in minutes.
The release marks a significant shift in how compliance setups are built. Until now, configuring a verification platform has required significant manual effort from solution architects or technical teams, including interpreting AML policies, translating regulatory requirements into platform settings, and building onboarding workflows by hand.
Also Read: “Disheveled,” “Not Coherent” — The Bias Is in the Notes, Not the AI
The new capabilities for compliance teams include policy-to-configuration, where teams upload their AML policy or regulatory requirements and ask an AI agent to configure their Sumsub environment from it. The agent reads the document, determines what is needed, and builds the settings live on the platform. Faster technical integration allows AI agents to handle the technical side of embedding Sumsub into a customer’s application, writing the necessary code and embedding verification as a mandatory step in an onboarding flow in real time. Teams can also use AI agents to manage compliance day to day, 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 works with any leading AI agent. Sumsub has published an open-source set of agent skills on GitHub, installable with a single terminal command.
The MCP integration builds on Sumsub’s broader AI strategy, which includes Summy, an AI Copilot for compliance and fraud teams inside the platform. These capabilities reflect Sumsub’s approach to building compliance infrastructure that works alongside the tools and workflows modern teams already use.
Also Read: 100 Things Google Announced at I/O 2026
Access to the MCP integration is restricted by separate permission to allow granular control over data. Sensitive actions are performed in an isolated sandbox, ensuring that configuration changes are always reviewed and approved by a human.
The integration is available now, with Sumsub becoming the first verification platform to be officially listed on the ChatGPT Apps platform. Further discussions are ongoing with additional LLMs. Full documentation and agent skills are publicly available via Sumsub’s developer resources.
