Netskope introduces security capabilities for Model Context Protocol (MCP) communication. The functionality is designed to help organizations deploy AI agents securely. MCP communication enables AI systems to connect to business data and issue autonomous commands.
MCP was launched by Anthropic in November 2024 as an open standard for connecting AI agents to external systems. The protocol acts as a universal adapter between AI applications and business assets. Adoption is growing rapidly: OpenAI, Google, and Amazon have embraced the protocol, and there are now thousands of publicly available MCP servers.
But that growth also comes with risks. Because MCP communication can give AI systems access to sensitive business data and enable autonomous commands, new security challenges arise. This is a particular concern with thousands of publicly available MCP servers.
Complete visibility and risk analysis
The new capabilities in the Netskope One platform provide organizations with complete visibility into MCP tool usage. The platform constantly identifies MCP servers and clients within the organization in real time, including attributes such as name, ID, URL, version, host, data source, and protocol.
Netskope is extending its Cloud Confidence Index (CCI) risk score to MCP servers. This allows organizations to quickly assess which AI tools, agents, or integrations pose the greatest security and compliance risk.
In addition, the platform can detect and monitor non-human traffic between MCP servers, clients, tools, hosts, and data sources. All MCP events are logged, including sessions, initializations, tool requests and responses, and deployments.
Granular access control and data loss prevention
Organizations can use the new functionality to manage access through granular, context-based policy controls. A default block option is also available for MCP traffic. Real-time data leak prevention, when used with MCP tools, is designed to protect sensitive information such as intellectual property and passwords.
“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 On.”
The new MCP capabilities are available immediately in preview for Netskope customers. General availability is expected in the first half of 2026.