Descope, a top provider of no, code identity solutions, has just unveiled a major upgrade to its Agentic Identity Hub 2. 0 identity platform that helps secure support for AI agents and Model Context Protocol (MCP) servers. This platform allows businesses to manage agent authentication, policy governance, and access control at the level of enterprise, grade precision.
Identity has become a significant challenge for developers and security teams due to the rapid use of AI agents in various industries. However, only 37% of companies have progressed beyond pilot projects, indicating that there are still major hurdles that need to be cleared to have secure, production, ready systems.
Enterprise-Grade Identity Controls for AI Agents
Agentic Identity Hub 2.0 treats AI agents as first-class identities, equipping them with dedicated credentials and contextual attributes like user association, tenant information, tool-level scopes, and OAuth client IDs. This comprehensive visibility helps organizations manage, monitor, and govern agent behavior across applications, APIs, and MCP infrastructure.
Key platform enhancements include:
- Centralized Agent Identity Management – Offers unified visibility of all agentic identities, whether dynamically created or manually registered, and connects them seamlessly to enterprise systems.
- Comprehensive MCP Authentication – Provides protocol-compliant authentication and access control for both internal and external MCP servers. Organizations can implement OAuth 2.1 flows, hardened dynamic client registration (DCR), Client ID Metadata Document (CIMD), tenant-level isolation, and per-tool scopes.
- Secure Credential Vault – Manages, stores, and refreshes ephemeral credentials, including OAuth tokens and API keys. Developers can rely on over 50 prebuilt connection templates to integrate AI agents securely with external services or downstream MCP endpoints.
- Enterprise-Grade Policy Enforcement – Enables fine-grained access policies defining which AI agents can access resources, what scopes they can invoke, and under which conditions actions are permitted.
- AI Agent Auditing and Logging – Delivers full audit trails and logging across agent lifecycle events, enabling real-time visibility, detection of misconfigurations, and integration with third-party SIEM platforms for extended security monitoring.
Also Read: Check Point Unveils AI-Driven Exposure Management to Close Cybersecurity Remediation Gap
Leadership Perspectives
“AI agents are breaking traditional identity systems,” stated Slavik Markovich, Co-founder and CEO of Descope. “They’re autonomous, scalable, and non-deterministic, meaning they can’t be managed like human users or service accounts. The Descope Agentic Identity Hub is a dedicated identity provider for AI agents, giving developers the abstraction layers they need to securely take their AI systems to market while ensuring least privilege access and ongoing protocol compliance. We’re grateful to the several customers already using the Agentic Identity Hub and are excited to be a part of the infrastructure layer needed for secure AI adoption.”
Echoing the value seen in the field, Soham Mazumdar, Co-founder and CEO of WisdomAI, shared: “The Descope Agentic Identity Hub frees up our developers from tooling and integration work so they can spend more time shipping core features instead. Our customer-facing MCP server uses Descope as the auth layer–this MCP server is used by Fortune 500 customers and helps us show the value of our AI-powered analytics platform while having the confidence that identity controls are baked-in.”
Highlighting the platform’s adaptability, Shreyans Mehta, co-founder and CTO of Cequence Security, said: “Descope is a key under-the-hood component of the Cequence AI Gateway. Descope’s flexible, developer-friendly handling of MCP auth has played an important role in helping Cequence AI Gateway customers securely connect their applications, APIs, and data to AI agents.”
Why Agentic Identity Matters
With the growing adoption of AI agents and MCP servers in enterprises, existing identity systems are unable to provide the necessary controls for secure and scalable deployments. Conventional models have difficulties dealing with transient credentials, delegated access, and real, time policy enforcement, which are crucial for modern AI and multi, agent systems. Agentic Identity Hub 2. 0 closes these points through a specially designed identity layer that can be easily integrated with the current enterprise IAM strategies.
