Descope Launches Agentic Identity Control Plane for AI Security
Descope introduces Agentic Identity Control Plane to enhance policy-based governance and identity management for AI agents and MCP ecosystems.
Descope has launched its Agentic Identity Control Plane, a solution designed to provide policy-based governance, auditing, and identity management for AI agents and Model Context Protocol (MCP) ecosystems. This release builds on the existing Descope Agentic Identity Hub, marking a significant step in Descope's mission to become the go-to identity provider for AI agents.
Growing Concerns Over AI Agent Security
As AI agents, large language models (LLMs), and MCP servers gain rapid adoption, security leaders are increasingly worried about unauthorized access and rogue AI agents. A survey of 400+ CIAM decision-makers commissioned by Descope revealed that 57% of respondents fear AI agents accessing or sharing unauthorized data. Notably, 5 of the OWASP Top 10 Threats for GenAI involve authentication and authorization issues.
Key Features of the Agentic Identity Control Plane
The new solution offers:
- Scope-based access control: A policy engine to restrict AI agent access to specific tools and enforce role-based policies.
- Monitoring and auditing: Enterprise-grade tools to track AI agent activity, detect misconfigurations, and identify rogue agents.
- End-to-end identity lifecycle management: Features like dynamic/static agent registration, user consent flows, and token management.
Industry Impact and Customer Adoption
Descope's no/low-code external IAM platform is already used by companies like GoFundMe, Databricks, Navan, and You.com to manage customer and machine identities. The Agentic Identity Hub, announced in April 2025, laid the groundwork for this release by addressing authentication challenges for AI-compatible APIs and MCP servers.
Executive Insight
Slavik Markovich, CEO of Descope, emphasized the importance of secure AI adoption: "No CISO wants to block agentic AI, but every new AI agent or MCP server introduces risk. Our Control Plane gives security teams the tools they need for scalable, secure AI integration."
For more details, visit Descope's LinkedIn.
Related News
AI Agents Pose New Security Challenges for Defenders
Palo Alto Networks' Kevin Kin discusses the growing security risks posed by AI agents and the difficulty in distinguishing their behavior from users.
AI OS Agents Pose Security Risks as Tech Giants Accelerate Development
New research highlights rapid advancements in AI systems that operate computers like humans, raising significant security and privacy concerns across industries.
About the Author
David Chen
AI Startup Analyst
Senior analyst focusing on AI startup ecosystem with 11 years of venture capital and startup analysis experience. Former member of Sequoia Capital AI investment team, now independent analyst writing AI startup and investment analysis articles for Forbes, Harvard Business Review and other publications.