Securing AI requires more than scanning models and flagging misconfigurations. Organizations are building with frontier models and open-source frameworks, deploying them across multiple clouds, wrapping them in agent frameworks, and connecting them to production data. Every layer introduces new risk, and the teams responsible for securing each layer are often working with different tools, different context, and different priorities. A deeply connected, open ecosystem, where every tool shares context and operates from the same source of truth, is what makes a resilient AI security program possible.
That’s what the Wiz Integration Network (WIN) was built for and today, we’re taking our connected ecosystem a step further by introducing agent integrations powered by the Wiz Model Context Protocol (MCP). This unlocks a brand-new way for partner AI agents to pull live Wiz context on demand, supported by the GA of the WIN partners endpoint in the Wiz MCP so partners can build certified integrations faster than ever.
A new way to integrate: your agent, Wiz’s context
For partners building AI agents, the MCP enables a new class of integration. Instead of batch API calls, your agent uses MCP tools to pull Wiz context such as Issues, Findings, and resources on demand as it works, directly from customer tenants. This enables richer investigation and faster response on your platform, powered by Wiz’s security graph.
For example, a partner’s security agent investigating a suspicious Issue can pull the full Issue context from Wiz mid-investigation – the affected resources, the toxic combination behind it, the blast radius, and the attack path – without the customer ever leaving the partner’s platform. The agent gets richer context, the investigation is faster, and the customer gets a more complete picture from the tools they’re already using.
Customers get a connected workflow where the security tools they already use pull Wiz context in real time, so investigations are richer, faster, and unified.
Build Fast with the WIN endpoint in Wiz MCP
To make building these agent-to-agent experiences just as fast as running them, the WIN partners endpoint in the Wiz MCP is now GA.
The endpoint lets partners build integrations with their own AI coding agents. Connect Claude Code, Cursor, GitHub Copilot, or any agent that supports remote MCP servers to the WIN partners endpoint, and your agent builds with the full knowledge of WIN’s APIs and documentation—so you ship higher quality integrations, faster, and reach customers sooner.
From there, your agent can:
Search WIN documentation: Pull tutorials, authentication guides, and certification requirements as it builds.
Retrieve API context: Fetch the exact API operation, filters, and required scopes so the code matches the current API without the back and forth.
Query demo environment data: Explore real Issues, Findings, and resources to understand the shape of the data before your integration ever touches a customer tenant.
Growing the WIN AI Ecosystem
Agent integrations build directly on the momentum of the AI category we launched in the Wiz Integration Network (WIN) earlier this year. Our goal has always been to bring together the best-of-breed AI and security tooling that organizations are leveraging across model providers, guardrail layers, agent frameworks, and more – giving them full visibility, protection, and defense across their stack as AI adoption continues to grow.
Since launching the category, we’ve added integrations with Anthropic (Claude), OpenAI, TrojAI, Pillar Security, Cloudflare, and more. Together, these integrations help teams:
Discover and inventory AI in their environment: Every AI service, model, and dataset running across your cloud, enriched with context from the Wiz Security Graph.
Enforce guardrails across AI workloads: Protect AI pipelines whether they’re built on self-hosted models, managed services, or third-party APIs.
Detect and respond to AI-specific threats: Defend against prompt injection, data poisoning, and AI-powered attacks with partners purpose-built for the AI threat landscape.
We’re continuing to grow the category because our customers are adopting AI faster than any single ecosystem can keep up with. If you’re building tools that help teams secure, govern, or operate AI, join WIN and let’s secure AI pipelines at AI speed.
Build the future of AI Security with WIN
Agent integrations are just the beginning. As AI adoption accelerates, the opportunities to build deeper, more connected experiences for mutual customers will only grow.
Through WIN, you get direct access to thousands of security and engineering teams, including over 65% of the Fortune 100, along with the tools to build fast and the go-to-market to reach customers together.
Whether you’re building an AI agent framework, a guardrail layer, an evaluation tool, or the next category-defining security product, join WIN to shape customers’ security experience. Ready to get started? Apply today, connect to the MCP, and let’s win AI with AI.
