News

Operant AI Unveils Security Platform for AI Agents Using MCP Standard

• By John K. Waters
• 06/29/2025

U.S.-based cybersecurity firm Operant AI on Saturday launched MCP Gateway, an extension of its AI Gatekeeper platform designed to provide runtime protection for enterprise deployments built on the Model Context Protocol (MCP). The new tool targets organizations adopting open-source MCP servers and AI agents, offering what the company calls the first enterprise-grade defense for securing these systems in real time.

The new system introduces monitoring, detection, and active protection for AI applications that connect to MCP-based infrastructure—ranging from developer tools like GitHub Copilot and Claude Desktop to remote agents operating on Kubernetes, AWS Bedrock, Azure, and Google Vertex AI.

"Organizations are deploying these powerful AI tools without visibility into what they're doing, what data they're accessing, or how they're being used," said Vrajesh Bhavsar, CEO and co-founder of Operant AI, in a statement. "MCP Gateway changes that by bringing comprehensive security, governance, and visibility to the entire MCP ecosystem."

Model Context Protocol (MCP) is an open standard developed by Anthropic to enable seamless integration among Large Language Models (LLMs) and external data sources and tools. It provides a standardized way for AI applications to access context, tools, and services, essentially acting as a universal adapter for LLMs.  Without MCP, you need to implement custom integrations for each tool that your LLM application needs to access.

However, this approach is hard to maintain and can cause issues when you want to scale your environment. With MCP, you can significantly speed up, simplify, and standardize these types of integrations.

Operant AI positions itself as the only runtime AI application defense platform. It was founded by Bhavsar, Priyanka Tembey, and Roof—former executives from Apple, VMware, and Google—and is backed by venture capital firms Felicis and SineWave. In 2024, the company was named a representative vendor in Gartner's Market Guide for AI Trust, Risk, and Security Management (AI TRiSM).

Operant AI, a San Francisco-based cybersecurity startup, specializes in runtime defense for AI and cloud applications. Founded by former executives from Apple, VMware, and Google—Vrajesh Bhavsar, Dr. Priyanka Tembey, and Ashley Roof—the company is backed by venture firms Felicis and SineWave Ventures. Operant was recently recognized as a representative vendor in Gartner’s Market Guide for AI Trust, Risk, and Security Management (AI TRiSM).

According to Operant, the rapid rise in MCP adoption presents a growing security challenge. MCP Gateway aims to address blind spots in enterprise environments by automatically identifying and managing interactions between AI agents and MCP servers.

The product offers real-time traffic mapping, agent discovery, and risk scoring for both local and cloud-based MCP implementations. Its feature set includes detection of sensitive data leakage, unauthorized access attempts, and potential jailbreaks. MCP Gateway also enforces access policies and rate limits for AI tool use, while supporting encryption and data redaction.

"We're not just securing MCP applications—we're enabling the entire ecosystem," said Ashley Roof, CMO and co-founder of Operant AI, in a statement. "Our partnership approach mirrors our successful sales enablement programs with model providers."

Operant said it is rolling out the platform with a broad ecosystem strategy, integrating its security tooling with vendors of MCP-compatible applications.

The gateway is now available through Operant's website, with support for major cloud platforms and AI development environments.