Sumsub have announced a Know Your Agent module for Model Context Protocol gateways. The company says the module is designed to sit between an AI agent and company data, applying access rules and filtering sensitive information before it reaches the agent.

The extension can request a liveness check when a workflow crosses a configured threshold, such as a high-value action. Sumsub also describes activity logging and configurable controls. The initial gateway integration is Amazon Bedrock AgentCore Gateway, with other gateways intended to follow.

This is an extension of Sumsub’s existing framework, not the first launch of Know Your Agent. The announcement establishes the vendor’s stated capabilities, but does not independently demonstrate their effectiveness against hostile agents or attempts to manipulate a human approver.

For financial services teams, the interesting design question is where to require intervention. Too many approval prompts can make a workflow unusable, while a broad authorisation at the start can leave later actions insufficiently constrained. A pilot could therefore test the approval boundary alongside data filtering and record whether the reviewer receives enough context to make a meaningful decision. Human presence alone does not establish that an action is appropriate.


AI for Leaders: Governance, Risk & Why Strategy Must Come First
Is your organisation adopting AI without a defined strategy or governance? If so, you're not alone — and the consequences range from data breaches to reputational damage to safeguarding failures. AI is a strategic risk, not a silver bullet, and definitely not a magic data fairy. Without clear ownership, rules, and accountability, AI can proliferate across your organisation in ways that cost more — in time, money, and trust — than not using it at all. Speakers: Craig Clark, Director at Clark & Company Information Governance Services, and Stewart Tinson, Project Director, AI-360. You'll learn: Why "understand your why" must precede any AI rollout Which risks senior leaders most commonly overlook — from data leakage to safeguarding How to measure AI value through outcomes, not adoption metrics Why accountability for AI governance sits with the C-suite, not IT or compliance Key topics: AI strategy • Risk appetite • Data protection • Bias & fairness • Safeguarding • AI literacy • Governance models • Return on investment • Executive accountability • AI use case tiering For CISOs, CIOs, and senior leaders who need to govern AI responsibly — before it governs them.
Share this post
The link has been copied!