August 7, 2025
5 min read
Industry News
Descope introduces Agentic Identity Control Plane for policy-based governance, monitoring, and identity management of AI agents and MCP ecosystems.
Descope Launches Agentic Identity Control Plane to Secure AI Agent Identities
Descope has launched the Agentic Identity Control Plane, a solution designed to enable security teams to implement policy-based governance, auditing, and identity management for AI agents and Model Context Protocol (MCP) ecosystems. This new platform builds upon the existing Descope Agentic Identity Hub and marks a significant advancement in Descope’s vision to become the identity provider for AI agents. As AI agents, large language models (LLMs), and MCP servers see rapid adoption, security leaders are increasingly concerned about unauthorized AI agent usage. Such unauthorized adoption can expand the attack surface, introduce compliance risks, and allow rogue AI agents to gain escalated privileges. A survey of over 400 CIAM decision-makers commissioned by Descope revealed that 57% of respondents worry about AI agents accessing or sharing data without proper authorization. Identity management is critical for secure agentic AI adoption, supported by the fact that five of the OWASP Top 10 Threats for GenAI involve authentication and authorization mitigations. Descope’s no-code/low-code external IAM platform helps organizations easily create, modify, and manage identity journeys for consumers, business customers, partners, AI agents, and MCP servers through visual workflows. Hundreds of customers, including GoFundMe, Databricks, Navan, and You.com, leverage Descope to enhance customer experience, prevent account takeover, and gain comprehensive visibility into customer and machine identities. In April 2025, Descope announced the Agentic Identity Hub, a suite of capabilities addressing authentication and authorization challenges for developers building AI-compatible APIs, remote MCP servers, and AI agents. The Agentic Identity Control Plane released today further enhances these offerings by providing enterprise security teams with critical oversight into identity management and governance for both internal and external AI systems.Key Capabilities of the Agentic Identity Control Plane
- Scope-based Access Control: A policy engine enables tight control over how AI agents and MCP clients/servers access corporate resources. Security teams can restrict AI agent access to specific scopes within third-party tools and enforce policies based on user roles and hierarchies.
- Enterprise-grade Monitoring and Auditing: Provides visibility into the AI agent risk surface, helps detect access control errors and misconfigurations, and identifies potential rogue AI agents before they cause damage.
- End-to-End Identity Lifecycle Management: Supports dynamic and static AI agent registration, configurable user consent flows, granular authorization scopes, token management and storage, and visibility into the relationships between AI agent identities and human identities. Slavik Markovich, CEO of Descope, stated, “No CISO wants to block the adoption of agentic AI and MCP at their company, but they are taking on an increased risk responsibility with every new AI agent or MCP server created within their organization or connecting with their products. The Agentic Identity Control Plane delivers easy to use and comprehensive policy control and monitoring tools that security teams need for secure, scalable AI adoption.”
- AI Agents: Capabilities, Risks, and Growing Role
- Understanding Model Context Protocol (MCP) and Why Publishers Should Care
- The Importance of AI Security in Financial Services
Source: Originally published at Help Net Security on August 6, 2025.