Netskope Advances the Safe Use of AI Agents with Model Context Protocol (MCP) Security Across the Enterprise

Rhea-AI Summary

Netskope (NASDAQ: NTSK) announced new security capabilities in the Netskope One platform to protect Model Context Protocol (MCP) communications that connect AI agents to enterprise data and tools. The features deliver real-time identification of MCP servers and clients (name, ID, URL, version, host, data source, protocol), extend the Netskope Cloud Confidence Index (CCI) risk scoring to MCP, enable granular context-based access policies (including a default block option), prevent data leaks, detect non-human MCP traffic, log MCP events, and identify sensitive data in MCP sessions.

The MCP security features are in Preview now for Netskope customers, with general availability expected in H1 2026. Netskope will demo the capabilities at AWS re:Invent in Las Vegas and offers more detail on its blog.

Positive

• Real-time identification of MCP servers and clients with detailed attributes
• Extension of Cloud Confidence Index risk scoring to MCP tools
• Granular, context-based policy controls including a default block option
• Event logging of MCP sessions, initializations, tool requests/responses, deployments

Negative

• Thousands of publicly available MCP servers create elevated security exposure
• Default block option for MCP traffic could disrupt legitimate agent workflows
• Feature set is currently in Preview; general availability expected in H1 2026

Insights

Cloud security product strategist

Netskope adds real-time MCP visibility and controls to Netskope One, helping enterprises manage AI agent risks.

In simple terms, Netskope now discovers MCP servers and clients continuously, scores MCP risk via the Cloud Confidence Index, and applies granular policies and data‑loss prevention to MCP traffic. The feature set covers identification, risk scoring, access control with a default block option, non‑human traffic detection, event logging, and sensitive‑data detection.

Key dependencies and risks include customer deployment speed and the accuracy of MCP detection and CCI scoring; limitations in either reduce effective protection. The capability is in Preview now and slated for general availability in the first half of calendar 2026, so practical value depends on adoption timing and proof points during Preview.

Watch for three monitorable items over the next 3–9 months: Preview feedback on MCP detection accuracy, early customer case studies showing prevented data exposure, and the formal GA rollout timing. These will clarify operational coverage and the platform\'s ability to block risky agent behaviors in production.

New Netskope One platform capabilities deliver visibility and access control for MCP, the emerging standard that enables AI agents to connect to enterprise data and tools

SANTA CLARA, Calif., Dec. 01, 2025 (GLOBE NEWSWIRE) -- Netskope (NASDAQ: NTSK), a leader in modern security and networking for the cloud and AI era, today announced breakthrough security capabilities for Model Context Protocol (MCP) communications. These enhancements are part of the Netskope One platform, which helps organizations confidently advance agentic AI adoption without compromising on security.

As AI adoption grows, MCP has emerged as a preferred method for connecting AI agents to enterprise resources. But because MCP communications are capable of connecting AI systems to enterprise data and facilitating autonomous commands, they also create new security risks, especially with thousands of publicly available MCP servers.

With the new platform capabilities, Netskope One can protect MCP-enabled AI interactions by providing full visibility into MCP tool use, enforcing least-privilege access, securing sensitive data, and ensuring compliance. Organizations using Netskope One can now:

• Identify MCP servers and clients in use within the organization constantly and in real time, including attributes such as name, ID, URL, version, host, data source, and protocol
• Extend Netskope Cloud Confidence Index (CCI) risk scoring to MCP servers, helping organizations quickly assess and prioritize which AI tools, agents, or integrations pose the greatest security and compliance risk
• Manage access using granular, context-based policy controls (including a default block option for MCP traffic) and real-time prevention of data leaks
• Detect and monitor non-human traffic between and across MCP servers, clients, tools, hosts, data sources, and development tools
• Log MCP events, including sessions, initializations, tool requests and responses, and deployments
• Identify sensitive data, such as intellectual property and passwords, in use with MCP tools

“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, 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. This is critical to the secure use of AI as organizations develop agents to drive business productivity.”

New MCP security capabilities are now in Preview to Netskope customers, with general availability expected in the first half of calendar 2026.

Read more about MCP security and our latest announcements on the Netskope blog.

Netskope will be demonstrating the full Netskope One platform, including new MCP security capabilities, at AWS re:Invent in Las Vegas this week. Engage with Netskope at AWS re:Invent by visiting booth #460, scheduling a session with Netskope experts, and joining Netskope speaking sessions and social events.

About Netskope
Netskope (NASDAQ: NTSK), a leader in modern security and networking for the cloud and AI era, addresses the needs of both security and networking teams by providing optimized access and real-time, context-based security for people, devices, and data anywhere they go. Thousands of customers, including more than 30% of the Fortune 100, trust the Netskope One platform, its Zero Trust Engine, and its powerful NewEdge network to reduce risk and gain full visibility and control over cloud, AI, SaaS, web, and private applications—providing security and accelerating performance without trade-offs.

Learn more at netskope.com, on LinkedIn, and on Instagram.

Media Contacts:
press@netskope.com

Investor Contacts:
investors@netskope.com

FAQ

What MCP security features did Netskope announce for NTSK on December 1, 2025?

Netskope added real-time MCP server/client identification, CCI risk scoring for MCP, granular context-based access controls (including a default block), data-leak prevention, non-human traffic detection, MCP event logging, and sensitive-data identification.

When will Netskope's MCP security capabilities for NTSK be generally available?

The MCP security capabilities are in Preview now with general availability expected in H1 2026.

How does Netskope's extension of the Cloud Confidence Index affect MCP tools for NTSK customers?

Extending CCI to MCP helps organizations assess and prioritize which AI tools, agents, or integrations pose the greatest security and compliance risk.

Will Netskope block MCP traffic by default for NTSK customers?

Netskope One supports a granular policy model that can include a default block option for MCP traffic, configurable by the organization.

Can Netskope One detect non-human MCP traffic for NTSK?

Yes; the platform can detect and monitor non-human traffic between MCP servers, clients, tools, hosts, and data sources.

Where will Netskope demonstrate the new MCP capabilities for NTSK?

Netskope will demonstrate the capabilities at AWS re:Invent in Las Vegas, including booth #460 and speaking sessions.