Strata Identity Announces New Way To Manage AI Agent Logins

Like human users, agents often have to login and authenticate into multiple systems within an enterprise.

Strata Identity, a provider of Identity Access Management (IAM), on Thursday announced a new product: Identity Orchestration for AI Agents.

AI can introduce a new issue with IAM platforms. According to a news release from Strata: “These agents are ephemeral and autonomous, accessing enterprise data through MCP (Model Context Protocol). As a result, they operate across systems using opaque credential flows without persistent attributes, dynamic provisioning, or audit trails. In hybrid environments spanning clouds, on-prem systems, and multiple IDPs, this creates blind spots in governance, inconsistent access control, and a higher risk of fraud and non-compliance.”

Strata says its product addresses these issues in a few ways:

• With “dynamic, runtime authentication for agents using delegated OAuth flows”
• With “policy-driven, attribute- and context-aware authorization”
• With “just-in-time issuance/provisioning of agent identities” into any cloud or on-premises IDP (Identity Provider).
• With “full-stack observability through Open Telemetry”

While Strata Identity is an IAM, it focuses on identity orchestration. That is a method of identity access and management bringing together disparate login and authentication identities into one seamless, cohesively managed identity. It has become a critical part of managing the many logins most users do every day and is considered an essential part of an organization's security infrastructure.

AI agents also require login and authentication.

“Autonomous AI agents now act as users in enterprise systems—but without user-level guardrails or observability. So Strata is bringing policy-based identity security to runtime where agents live,” said Eric Olden, CEO of Strata Identity and co-author of the SAML standard in a news release. “It supports open identity frameworks such as OAuth and emerging standards like the AI-native MCP protocol, enabling seamless interoperability across vendors, platforms, and agent ecosystems at scale.”

“AI agents aren’t just a new type of identity; they’re a new class of actor entirely. They don’t follow the rules we’ve used to manage humans or machines. Instead, they operate independently, make decisions in real time, and interact with systems across cloud and on-prem environments. Traditional IAM systems were never designed for this level of autonomy, speed, or scale,” Olden also wrote in a blog post.