Databricks expanded AI Gateway to provide governance for agentic AI systems that orchestrate multi-step workflows across models and tools. New features include MCP server governance to control agent access to external systems, unified audit logging, access controls, and cost tracking. This addresses visibility and compliance challenges when agents call LLMs, databases, APIs, and tools like Cursor and Claude Code.
Products
AI Gateway: A Governance Layer for Agentic AI
Databricks expanded AI Gateway with MCP server governance and unified audit logging to give enterprises visibility and control over agentic AI systems orchestrating multi-tool workflows.
Wednesday, April 15, 2026 12:00 PM UTC2 MIN READSOURCE: Databricks BlogBY sys://pipeline
Tags
products
/// RELATED
InfrastructureApr 22
The eighth-generation TPU: An architecture deep dive
Google's TPU 8t and 8i variants eliminate data-preparation bottlenecks with custom Axion CPUs, delivering specialized training and inference hardware optimized for world models and agentic AI at scale.
Policy4d ago
Eden: NHS goes to war against open source
NHS closes open-source repositories over fears of Anthropic's Mythos LLM scanner despite minimal actual security risk, contradicting UK Tech Code of Practice.