What platforms and LLMs does Cortex AI Gateway support?

The gateway governs AI agents across first-party tools (Snowflake CoCo, CoWork) and third-party ecosystems including Amazon Bedrock, Azure AI Foundry, ChatGPT, Claude Code, Cursor, custom LangChain or LlamaIndex apps, and others. The private-preview Wide Model Catalog enables access to GPT, Gemini, Claude, Grok, Mistral, GLM and more, all runnable in your chosen geography.

When are the features available, and which are still in preview?

Cortex AI Gateway is available now; Agent Identity, Restricted Session Scope (GA soon), Native AI Security Posture Management, and Ransomware Protection via Multi-Party Approval are in general availability (GA). Private preview features include Wide Model Catalog, Access Governance and Sprawl Control, Govern Every Agent Connection (100+ MCP servers), Observability and Tracing, Agent Action Auditability, AI Cost Control, Intelligent Model Routing, Context-Aware Access Policies, Advanced Data Exfiltration Prevention, and Client-side CoCo CLI VM Sandbox (macOS only).

How does the gateway control AI costs?

AI Cost Control (in private preview) provides a unified view of AI consumption by team, agent or workload, allows management and application of budget guardrails, and routes requests to cheaper models for simpler tasks. Intelligent Model Routing (private preview) automatically directs requests to the right model based on cost, latency, capability and data residency requirements.

AI Safety & AlignmentAI Business & IndustrySnowflake AI BlogJul 29, 2026Jul 29, 2026, 13:01 JST

Snowflake launches AI Gateway to secure autonomous agents amid rising security concerns

Send on LINE

3 Key Points

What happened
Snowflake announced Cortex AI Gateway at Black Hat 2026, integrating a centralized MCP (Model Context Protocol) gateway called Natoma to govern how AI agents access models, data, and enterprise tools across first-party (Snowflake CoCo, CoWork) and third-party platforms (Amazon Bedrock, Azure AI Foundry, ChatGPT, Claude Code, Cursor, and custom apps). The company also moved several AI security features to general availability (GA) or public preview, including Agent Identity (GA), Restricted Session Scope (GA soon), Native AI Security Posture Management (GA), and Ransomware Protection via Multi-Party Approval (GA).
Why it matters
AI security concerns jumped from 17% in 2024 to 48% in 2026 according to The Linux Foundation's 2026 State of Tech Talent Report, while 97% of organizations aim to implement AI yet 57% face a significant capacity gap in security and risk management. Autonomous agents have dramatically expanded the enterprise attack surface by combining data access, system execution, and data movement, leaving organizations vulnerable to unvetted servers, tool hijacking, and data exfiltration. Snowflake's unified gateway and security stack aim to solve the fragmented visibility, unmanaged sprawl, and spiraling AI costs that currently plague decentralized agent deployments.
What to watch
Cortex AI Gateway is available now as the first milestone on Snowflake's AI gateway roadmap. Several features are in private preview—Wide Model Catalog (bringing GPT, Gemini, Claude, Grok, Mistral, GLM and others under one roof), Access Governance and Sprawl Control, Govern Every Agent Connection (100+ MCP servers), Observability and Tracing, Agent Action Auditability, AI Cost Control, Intelligent Model Routing, Context-Aware Access Policies, Advanced Data Exfiltration Prevention, and Client-side CoCo CLI VM Sandbox (macOS only). Demonstrations will be available at the Snowflake booth (#8206) at Black Hat USA 2026.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Get news like this every morning, free

Context & Analysis

The jump in AI security concerns from 17% in 2024 to 48% in 2026 signals a fundamental shift in enterprise priorities. While 97% of organizations are committed to implementing AI, the 57% facing a significant capacity gap in security and risk management reveals a dangerous mismatch between ambition and preparedness. Autonomous agents have become the focal point of this tension: they combine data access, system execution, and data movement into single profiles that vastly expand the attack surface, yet many organizations rely on fragmented, application-layer fixes and legacy monitoring tools that cannot keep pace.

Snowflake's announcement addresses this structural vulnerability directly. By embedding Natoma—a centralized MCP gateway—into its ecosystem, the company is attempting to enforce identity, policy, and audit at the tool-call level, thereby converting a decentralized, unmanaged sprawl into a unified control plane. The breadth of third-party integrations (1Password, Aembit, Cyera, Linx Security, Okta, SailPoint, Saviynt) and platform support (Amazon Bedrock, Azure AI Foundry, ChatGPT, Claude Code, Cursor, custom frameworks) signals that Snowflake sees the security problem as industry-wide and requiring interoperability, not proprietary lock-in.

The security features moving to GA—Agent Identity, Restricted Session Scope, Native AI Security Posture Management, and Ransomware Protection via Multi-Party Approval—indicate that Snowflake views agent identity governance and zero-trust principles as production-grade necessities. The private-preview Data Exfiltration Prevention and CoCo CLI VM Sandbox underscore a defense-in-depth philosophy: security controls are layered across identity, network, data movement, and workload isolation, rather than concentrated at any single point.

FAQ

What platforms and LLMs does Cortex AI Gateway support?: The gateway governs AI agents across first-party tools (Snowflake CoCo, CoWork) and third-party ecosystems including Amazon Bedrock, Azure AI Foundry, ChatGPT, Claude Code, Cursor, custom LangChain or LlamaIndex apps, and others. The private-preview Wide Model Catalog enables access to GPT, Gemini, Claude, Grok, Mistral, GLM and more, all runnable in your chosen geography.
When are the features available, and which are still in preview?: Cortex AI Gateway is available now; Agent Identity, Restricted Session Scope (GA soon), Native AI Security Posture Management, and Ransomware Protection via Multi-Party Approval are in general availability (GA). Private preview features include Wide Model Catalog, Access Governance and Sprawl Control, Govern Every Agent Connection (100+ MCP servers), Observability and Tracing, Agent Action Auditability, AI Cost Control, Intelligent Model Routing, Context-Aware Access Policies, Advanced Data Exfiltration Prevention, and Client-side CoCo CLI VM Sandbox (macOS only).
How does the gateway control AI costs?: AI Cost Control (in private preview) provides a unified view of AI consumption by team, agent or workload, allows management and application of budget guardrails, and routes requests to cheaper models for simpler tasks. Intelligent Model Routing (private preview) automatically directs requests to the right model based on cost, latency, capability and data residency requirements.

Snowflake AI BlogRead Original Article

Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Get it free

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.