Cloud security company Netskope Inc. today announced new security capabilities for the Model Context Protocol that help organizations confidently advance agentic artificial intelligence adoption without compromising on security.

The new capabilities, delivered through the Netskope One platform, are aimed at giving organizations greater visibility and control over AI agents as they move beyond experimental deployments and into production use.

MCP, which is a rapidly emerging standard that allows AI agents to connect directly to enterprise data, tools and workflows, can create new security risks, especially with thousands of publicly available MCP servers. The new capabilities released today are targeted at the potential security risks MCP introduces.

With the update, Netskope One can now automatically discover and identify both MCP servers and MCP-enabled clients operating on enterprise networks. The platform provides detailed metadata on each MCP component, including host details, identity attributes and version information to allow security teams to understand exactly where agentic AI activity is occurring.

Complementing the discovery capability is risk scoring that uses Netskope’s Cloud Confidence Index to allow organizations to assess the relative security posture of different MCP-powered tools and integrations.

The updates also see the introduction of granular policy controls for MCP traffic that allow security teams to define which AI agents are allowed to access which enterprise resources, with the option to block unapproved activity by default.

The platform supports real-time inspection of MCP sessions, detection of non-human traffic patterns associated with AI agents and full event logging for auditing and forensic analysis. Built-in data loss prevention capabilities further allow organizations to detect when sensitive data such as source code, credentials, personal data, or regulated information is being accessed or transferred through AI agents.

“Every team wants to confidently accelerate AI adoption and emerging protocols such as MCP are now fundamental to that discussion,” said John Martin, chief product officer at Netskope. “MCP also creates new security risks that legacy tools can’t solve. That’s why we’re further extending the market-leading capabilities of Netskope One to enable teams to see and create policies for MCP traffic and immediately assess how risky MCP tools are.”

New MCP security capabilities are available from today in preview to Netskope customers, with the company planning to make the new capabilities generally available in the first half of 2026.

Photo: Netskope