Artificial intelligence security platform company TrojAI Inc. today announced the launch of TrojAI Defend for MCP, a new AI runtime defense solution for agentic AI workflows.
TrojAI Defend for MCP has been built to monitor traffic to and from Model Context Protocol servers to provide unified visibility, policy analysis and runtime enforcement across agents and MCP gateways.
MCP, which is an open standard that lets AI agents securely connect to external data, tools and services in a consistent, structured way, has rapidly grown in popularity along with the rise of AI use in the enterprise. However, TrojAI argues that MCP adoption has also seen the emergence of a new class of operational and security risks.
Unauthorized MCP servers and agents can emerge outside approved governance, while unvetted tools can execute malicious code or exfiltrate sensitive data. TrojAI also says that tool definitions themselves can drift, be tampered with, or be poisoned, leading to altered instructions and hidden payloads.
Organizations must now monitor for data leakage, privilege escalation, cross-agent manipulation and compliance breaches within this new runtime layer.
TrojAI Defend for MCP gives security teams the visibility, policy control and runtime enforcement needed to secure MCP deployments. The new offering extends TrojAI’s existing Defend offering to the MCP layer to ensure that every server, agent and tool operates within approved governance and audit frameworks.
The new service includes MCP Server Registry and Tool Approval, which discovers all MCP servers in an organization’s environment and registers approved servers to eliminate “shadow” MCP instances. Another feature, MCP Traffic Visibility, monitors all MCP traffic, including prompts and responses, to and from each server and blocks connections to unregistered or rogue servers, eliminating hidden communication paths.
TrojAI Defend for MCP can also detect and prevent tool change by continuously tracking changes in tool definitions to prevent tampering, drift, or poisoning. A complimentary MCP Policy Engine can apply MCP-specific policies that inspect, audit and enforce security in real time.
“With TrojAI Defend for MCP, we are enabling the adoption of agents using MCP by ensuring these advanced workflows are secure,” said Lee Weiner, chief executive officer of TrojAI. “By monitoring agentic workflows in real time in production systems, TrojAI Defend for MCP helps customers not just keep pace with new and evolving threats but get ahead of them.”
TrojAI is a venture capital-backed startup that has raised $11.4 million over five rounds, according to data from Tracxn. Investors in the company include Flying Fish Ventures, Build Ventures, Techstars Central, Flybridge Capital Partners and Alteryx Inc.
Image: TrojAI
Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.
- 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more
- 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network.
About News Media
Founded by tech visionaries John Furrier and Dave Vellante, News Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.
