← All updates Databricks Update One-Pager Light version
databricks Platform · Updated Apr 15, 2026

AI Gateway now governs MCP servers (Beta)

You can now use AI Gateway to enforce access control, monitor usage, and audit activity across all MCP interactions in your workspace.

Beta Open docs ↗release note ↗
What it does

You can now use AI Gateway to enforce access control, monitor usage, and audit activity across all MCP interactions in your workspace. AI Gateway is the Databricks central governance layer for LLM endpoints, coding agents, and MCP servers. Beta This page covers the new Unity AI Gateway (visible in the sidebar of the UI), which is currently in Beta.

Why it matters

AI Gateway is the Databricks central governance layer for LLM endpoints, coding agents, and MCP servers.

Key capabilities
AI governance guide
AI governance guide
An end-to-end path for administrators
An end-to-end path for administrators to govern access to AI assets, traffic and cost, and the content of requests and responses.
Tutorial: Govern a coding agent's
Tutorial: Govern a coding agent's GitHub MCP access
Restrict a coding agent's access
Restrict a coding agent's access to GitHub MCP tools using Unity Catalog permissions and a built-in service policy.
Architecture
Databricks Platform → Platform
In short

You can now use AI Gateway to enforce access control, monitor usage, and audit activity across all MCP interactions in your workspace. AI Gateway is the Databricks central governance layer for LLM endpoints, coding agents, and MCP servers.

Read the full documentation ↗
Key takeaway
You can now use AI Gateway to enforce access control, monitor usage, and audit activity across all MCP interactions in your workspace.
2026-04-15-ai-gateway-now-governs-mcp-servers-beta Generated by the Databricks Updates Agent · browse all updates