Harness Integrates Agentic Security with Google Cloud Apigee

Integration gives Apigee customers real-time discovery, runtime protection, and full observability for agentic AI

Harness, the AI Software Delivery Platform™ company, today announced it has integrated capabilities with Google Cloud’s Apigee, a platform for API development and management, to help customers discover and protect agents, AI services, tools, and MCP workflows.

Also Read: Top Infrastructure as Code, DevOps & Cloud Conferences to Attend in 2026

Blindly applying traditional AppSec to agent development doesn’t work. The assumptions don’t hold, the tools don’t reach, and the attack surface keeps evolving and expanding. What’s needed isn’t a patch on existing practice; it’s a purpose-built approach that secures agents at every stage of how they’re actually built and run. And it’s critical that companies protect agents at the speed at which they’re being built.

74% of developers see security as a blocker to AI innovation, according to The Harness State of AI-Native Application Security 2025 report. In turn, 62% of security respondents said developers weren’t taking responsibility for securing AI-native apps like agents. The Harness and Apigee integration help organizations put security and developers on the same team – innovating at machine speed while keeping their agents, AI services, and MCP workflows secure.

“Organizations are innovating with agents at breakneck speed,” said Rahul Sood, GM of Application Security at Harness. “As they innovate and adopt new capabilities, they are forcing security teams to keep pace. This integration allows customers building on Apigee to seamlessly detect and protect agents as they are being deployed so developers can innovate confidently.”

Harness has long collaborated with Google Cloud, from bringing AI into software delivery to unifying AI intelligence across the delivery lifecycle. That work earned Harness recognition as the 2026 Google Cloud Technology Partner of the Year for DevOps and now extends beyond DevOps and into application security for AI agents.

The new integration brings intelligence provided by Harness AI Security directly into the API control layer. Enterprises can discover, monitor, and protect all of their agentic assets: every agent, AI asset, tool, LLM-powered service, and MCP-connected workflow that traverses it.

Security That Speeds Innovation Instead of Slowing It Down

As enterprises deploy AI agents and LLM powered applications, Google Cloud’s Apigee increasingly sits on the path between users, applications, models, tools, and backend APIs. By adding Harness AI and agent security intelligence into this API control layer, customers can extend their existing API security architecture to new AI interaction patterns without creating a separate operational model. This integrated approach allows security to automatically discover agents and other AI assets as they’re being deployed, closing the gap between development, deployment, and security.

Also Read: Infrastructure as Code vs Configuration Management: What’s the Difference?

“Securing AI agents and emerging technologies requires a paradigm shift in how we think about enterprise protection,” said Ritika Suri, Managing Director, AI & Data ISV Partnerships, Google Cloud. “Through our collaboration with Harness, we are bringing robust, agent-aware security to our joint customers without compromising on the agility to deliver solutions that help organizations innovate with confidence.”

Harness’s agentic security integration with Google Cloud’s Apigee provides organizations with:

• Agent and AI Discovery: Harness automatically inventories every AI asset, MCP server, tool, prompt and resource traversing Apigee. Agent discovery also goes beyond individual AI assets by introducing an agent SPM capability that continuously surfaces agents as they spin up, maps how AI assets connect and chain, and assesses their posture across the organization.
• AI Firewall protects agents and all AI assets at runtime, enforcing policy continuously against suspicious agent-to-agent communication, prompt injection, tool misuse, and data exfiltration through agentic chains – after the agent is live and as long as it runs.
• AgentTrace brings observability throughout the entire agent activity session, providing a full audit trail across prompts, reasoning, tool calls, and outputs. This is especially important for agentic operations to have confidence that the non-deterministic systems are acting as expected.

With reduced blind spots, faster incident investigation, and trace-level context across API and AI integrations, enterprises can innovate confidently and at the speed they need.

Write to us [⁠wasim.a@demandmediaagency.com] to learn more about our exclusive editorial packages and programmes.