Articles tagged agentic-ai
Introducing xaa.dev: A Playground for Cross App Access
AI agents are quickly becoming part of everyday enterprise development. They summarize emails, coordinate calendars, query internal systems, and automate workflows across tools. But once an AI agent needs to access an enterprise application on behalf of a user, things get complicated. How do you securely let an AI-powered app act for a user without exposing credentials, spamming consent prompts, or losing administrative control? This is the problem Cross App Access (XAA) is designed to...
Okta Developer Connect Recap
Identity has become one of the most important control points in modern systems. As applications grow more distributed and AI-driven automation becomes part of everyday workflows, identity increasingly defines how secure, predictable, and trustworthy those systems are. Decisions about access, scope, and lifecycle now shape not only the user experience, but also how well security holds up as systems scale. With this shift in mind, we hosted our first flagship Okta Developer Connect event in...
Introducing the Okta MCP Server
As AI agents and AI threats proliferate at an unprecedented rate, it becomes imperative to enable them to communicate safely with the backend systems that matter the most. A Model Context Protocol (MCP) server acts as the bridge between an LLM and an external system. It translates natural language intent into structured API calls, enabling agents to perform tasks like provisioning users, managing groups, or pulling reports, all while respecting the system’s security model. Establishing...
Build Secure Agent-to-App Connections with Cross App Access (XAA)
Secure access with enterprise IT oversight between independent applications that communicate with each other is a recognized gap in OAuth 2.0. Enterprises can’t effectively regulate cross-app communication, as OAuth 2.0 consent screens rely on users granting access to their individual accounts. Now, with the advent of AI agents that communicate across systems, the need to solve the gap is even greater – especially given the growing importance of enterprise AI security in protecting sensitive data...