Expanding Agent Governance with Unity AI Gateway

DATA + AI SUMMIT ![Image 8: Data+ai summit promo JUNE 15–18|SAN FRANCISCO Last chance to save 50% — ends April 30. Register](http://www.databricks.com/dataaisummit?itm_source=www&itm_category=home&itm_page=home&itm_location=navigation&itm_component=navigation&itm_offer=dataaisummit)

Blog
/ Product
/ Article

* *

Contents in this story

Reliability and Flexibility for Production

Expanding Agent Governance with Unity AI Gateway

Control and audit AI agents and coding assistants with unified governance, visibility and guardrails

Published: April 15, 2026

Product5 min read

by David Nasi

Share this post

[](https://www.linkedin.com/shareArticle?mini=true&url=https://www.databricks.com/blog/ai-gateway-governance-layer-agentic-ai&summary=&source=)
[](https://twitter.com/intent/tweet?text=https://www.databricks.com/blog/ai-gateway-governance-layer-agentic-ai)
[](https://www.facebook.com/sharer/sharer.php?u=https://www.databricks.com/blog/ai-gateway-governance-layer-agentic-ai)

Keep up with us

Subscribe

#### Summary

Now supporting MCP governance: Control which agents can access external systems with fine-grained permissions, including on-behalf-of (OBO) access.
End-to-end observability for agents: Monitor LLM and MCP calls, monitor usage, and attribute costs across models, teams, and workflows.
More flexible and reliable model access: Use a unified API across models with built-in fallbacks, rate limits, and guardrails.

Today, we are announcing major enhancements to AI Gateway. As part of this release, AI Gateway is now part of Unity Catalog as Unity AI Gateway. This extends Unity Catalog’s governance model to agentic AI, so you can apply the same permissions, auditing, and policy controls to how agents access LLMs and interact with tools like MCP servers and APIs.

Here’s what happens when an AI agent answers a customer question: it calls an LLM to interpret the query, pulls order history from Salesforce via an MCP server, checks real-time shipping data through an internal API, and then calls the LLM again to draft a response. Total time: under a second. Total visibility into who accessed what data, which systems were called, and whether policies were followed: almost none.

What’s changed isn’t just the tools—it’s the architecture. AI agents now orchestrate multi-step workflows across models and systems, often touching sensitive data at every step. That could mean querying a database, calling an external API, or using coding agents like Cursor, Codex, or Claude Code to generate or modify code.

And that raises new questions: Who authorized each action? What data was shared with which model? Were policies enforced consistently? If something breaks, can you trace the full chain?

Traditional governance tools weren’t built for this world. They operate in silos and can’t provide a unified view across the full lifecycle of an agent’s actions.

With this release, we’re expanding Unity Catalog’s governance capabilities to cover AI agents. Unity AI Gateway lets you control LLM access, govern how agents use MCP servers and APIs, and apply consistent policies across models and tools. This includes new support for MCP governance, so you can control which agents can access which external systems and track how that data is used. For a deeper look, read ourhow-to blog on connecting agents to external MCPs securely.

You also get detailed observability across both LLM and MCP calls, along with granular cost tracking across models, teams, and workflows. In addition, Unity AI Gateway provides a unified way to work across models, with built-in fallbacks, rate limits, and guardrails to help you run agents reliably in production.

Some of the capabilities described below are available in Beta

You can now set up a new LLM endpoint or MCP server in seconds—choose your model (Claude Opus 4.6, GPT-4, Gemini, Llama, or any provider-native API) and configure governance once. The same framework applies across Anthropic, OpenAI, Google, and open-source models.

Give your support team a Claude endpoint for conversational AI. Use GPT-4 for structured data extraction. Equip your engineers with Codex or Claude for coding agents. Bring in Gemini for multimodal workflows. You can choose the right model for each task without reworking governance each time. Policies stay consistent across providers—no duplicate setup, no separate configurations to manage.

Image 12: AI Gateway endpoint configuration

Fine-Grained Permissions and Guardrails

Fine-grained permissions and guardrails prevent what shouldn't happen in the first place.

Granular access control for tools

When agents call MCP servers to access internal systems, Unity AI Gateway supportson-behalf-of user execution. The MCP executes with the requesting user's exact permissions, not a shared service account. If a user can't access a Salesforce record, neither can the agent—even with elevated privileges.

Flexible guardrails powered by LLM judges (Beta)

Unity AI Gateway's guardrails use a prompt + model approach—configure them to run on requests, responses, or both:

PII Detection & Redaction: Detects and masks emails, SSNs, phone numbers before they reach external models
Content Safety: Block toxic, harmful, or inappropriate content with customizable filters
Prompt Injection Detection: Catch jailbreak attempts trying to override system instructions
Data Exfiltration Prevention: Prevent exposure of training data or proprietary content
Hallucination Guard: Validate responses against grounding sources
Custom Guardrails: Define your own with a custom prompt and model

Each guardrail is backed by an editable prompt and configurable model—not rigid pre-built logic. When violated, Unity AI Gateway can reject the request or mask sensitive data. All actions get logged for audit. This capability is currently rolling out and will be available in all supported regions within the next week.

End-to-End Observability

Three teams need answers when AI agents hit production: FinOps wants to know what's costing money, engineering needs to debug failures, security needs audit trails. Unity AI Gateway gives each team what they need from the same unified logging infrastructure.

Image 13: AI Gateway Usage Analytics Dashboard

For FinOps: Track costs by what matters to you

Every request gets logged toUnity Catalog system tables with actual dollar costs—not just token counts. Provisioned throughput uptime, pay-per-token usage, and external model pricing all calculated automatically. Slice costs however your organization budgets:

Endpoint tags: Group by team, environment, or cost center
Request tags: Dynamic attribution for SaaS platforms proxying to end customers
Identity: Aggregate by user or service principal—map spend to budget owners
Model and provider: Track which models (Opus vs Sonnet) and providers (Anthropic vs OpenAI) drive costs

For Engineering: Full payloads for debugging

Enable**inference tables**that capture complete request/response payloads, latency, status codes, and errors to Delta tables. When an agent fails, trace exactly what prompt was sent, what the model returned, and where it broke—and use tools like Genie Code and MLflow to quickly debug and resolve issues.

For Security: Complete audit trails

Every request logs the requesting identity, timestamp, and—for MCP calls—connection name, HTTP method, and whether the call was on-behalf-of user. Unity Catalog permissions control who sees what.

A single logging infrastructure powers three critical use cases—built on Delta tables you own and control.

Reliability and Flexibility for Production

Unity AI Gateway gives you flexibility in how you call models, depending on what your application needs.

Unified APIs for seamless provider switching (Beta)

If portability matters—and it should—use Unity AI Gateway's OpenAI-compatible API. Your code stays the same across every provider. Write your application once, then switch between any model by updating the endpoint configuration. No code changes, no redeployment.

Automatic failover keeps systems running (Beta)

Configurefallback models, and Unity AI Gateway handles failures automatically. If your primary model hits rate limits or returns errors, requests route to your backup model in sequence until one succeeds. Opus quota exhausted? Traffic falls back to Sonnet. Provider experiencing an outage? Your application routes to an alternative. No manual intervention, no downtime.

Finally, Unity AI Gateway enables you to set rate limits at the endpoint, user, or group level to prevent runaway costs and protect your SLA before problems start.

GUIDE

Your compact guide to modern analytics

Read now

Get Started with Unity AI Gateway

The new capabilities described above are available in supported Databricks regions. Open your workspace,navigate to Unity AI Gateway in the sidebar, and start governing your GenAI stack—LLMs and MCPs—from one place. Learn more in thedocumentation and thehow-to blog on connecting agents to external MCPs securely.

Keep up with us

Subscribe

Contents in this story

Reliability and Flexibility for Production

Recommended for you

Image 18: Agent Bricks: The Governed Enterprise Agent Platform

Product

April 14, 2026/6 min read

#### Agent Bricks: The Governed Enterprise Agent Platform

Product

April 15, 2026/3 min read

#### AI Gateway: How to Connect Agents to External MCPs Securely

April 14, 2026/6 min read

#### Agentic Reasoning in Practice: Making Sense of Structured and Unstructured Data

Share this post

[](https://www.linkedin.com/shareArticle?mini=true&url=https://www.databricks.com/blog/ai-gateway-governance-layer-agentic-ai&summary=&source=)
[](https://twitter.com/intent/tweet?text=https://www.databricks.com/blog/ai-gateway-governance-layer-agentic-ai)
[](https://www.facebook.com/sharer/sharer.php?u=https://www.databricks.com/blog/ai-gateway-governance-layer-agentic-ai)

Never miss a Databricks post

Subscribe to our blog and get the latest posts delivered to your inbox

Sign up

*

Work Email

*

Country:

By clicking “Subscribe” I understand that I will receive Databricks communications, and I agree to Databricks processing my personal data in accordance with its Privacy Policy.

Subscribe

What's next?

Image 24: Introducing Predictive Optimization for Statistics

Product

November 20, 2024/4 min read

#### Introducing Predictive Optimization for Statistics

Image 26: How to present and share your Notebook insights in AI/BI Dashboards

Product

November 21, 2024/3 min read

#### How to present and share your Notebook insights in AI/BI Dashboards

Image 28: databricks logo

Why Databricks

Discover

Customers

Customer Stories

Partners

Why Databricks

Discover

Customers

Customer Stories

Partners

Product

Databricks Platform

Pricing

Open Source

Integrations and Data

Product

Databricks Platform

Pricing

Open Source

Integrations and Data

Solutions

Databricks For Industries

Cross Industry Solutions

Data Migration

Professional Services

Solution Accelerators

Solutions

Databricks For Industries

Cross Industry Solutions

Data Migration

Professional Services

Solution Accelerators

Resources

Documentation

Customer Support

Community

Learning

Events

Blog and Podcasts

Resources

Documentation

Customer Support

Community

Learning

Events

Blog and Podcasts

About

Company

Careers

Press

Security and Trust

About

Company

Careers

Press

Security and Trust

Image 30: databricks logo

Databricks Inc.

160 Spear Street, 15th Floor

San Francisco, CA 94105

1-866-330-0121

[](https://www.linkedin.com/company/databricks)
[](https://www.facebook.com/pages/Databricks/560203607379694)
[](https://twitter.com/databricks)
[](https://www.databricks.com/feed)
[](https://www.glassdoor.com/Overview/Working-at-Databricks-EI_IE954734.11,21.htm)
[](https://www.youtube.com/@Databricks)

Image 32

See Careers

at Databricks

[](https://www.linkedin.com/company/databricks)
[](https://www.facebook.com/pages/Databricks/560203607379694)
[](https://twitter.com/databricks)
[](https://www.databricks.com/feed)
[](https://www.glassdoor.com/Overview/Working-at-Databricks-EI_IE954734.11,21.htm)
[](https://www.youtube.com/@Databricks)

We Care About Your Privacy

Databricks uses cookies and similar technologies to enhance site navigation, analyze site usage, personalize content and ads, and as further described in our Cookie Notice. To disable non-essential cookies, click “Reject All”. You can also manage your cookie settings by clicking “Manage Preferences.”

Manage Preferences

Reject All Accept All

Image 36: Databricks Company Logo

Privacy Preference Center

Opt-Out Preference Signal Honored

Privacy Preference Center

### Your Privacy
### Strictly Necessary Cookies
### Performance Cookies
### Functional Cookies
### Targeting Cookies
### TOTHR

#### Your Privacy

When you visit any website, it may store or retrieve information on your browser, mostly in the form of cookies. This information might be about you, your preferences or your device and is mostly used to make the site work as you expect it to. The information does not usually directly identify you, but it can give you a more personalized web experience. Because we respect your right to privacy, you can choose not to allow some types of cookies. Click on the different category headings to find out more and change our default settings. However, blocking some types of cookies may impact your experience of the site and the services we are able to offer.

#### Opting out of sales, sharing, and targeted advertising

Depending on your location, you may have the right to opt out of the “sale” or “sharing” of your personal information or the processing of your personal information for purposes of online “targeted advertising.” You can opt out based on cookies and similar identifiers by disabling optional cookies here. To opt out based on other identifiers (such as your email address), submit a request in our Privacy Request Center.

More information

#### Strictly Necessary Cookies

Always Active

These cookies are necessary for the website to function and cannot be switched off in our systems. They assist with essential site functionality such as setting your privacy preferences, logging in or filling in forms. You can set your browser to block or alert you about these cookies, but some parts of the site will no longer work.

#### Performance Cookies

[x] Performance Cookies

These cookies allow us to count visits and traffic sources so we can measure and improve the performance of our site. They help us to know which pages are the most and least popular and see how visitors move around the site.

#### Functional Cookies

[x] Functional Cookies

These cookies enable the website to provide enhanced functionality and personalization. They may be set by us or by third party providers whose services we have added to our pages. If you do not allow these cookies then some or all of these services may not function properly.

#### Targeting Cookies

[x] Targeting Cookies

These cookies may be set through our site by our advertising partners. They may be used by those companies to build a profile of your interests and show you relevant advertisements on other sites. If you do not allow these cookies, you will experience less targeted advertising.

#### TOTHR

[x] TOTHR

Cookie List

Consent Leg.Interest

[x] checkbox label label

[x] checkbox label label

[x] checkbox label label

Clear

- [x] checkbox label label

Apply Cancel

Confirm My Choices

Allow All

Expanding Agent Governance with Unity AI Gateway

TL;DR · AI 摘要

核心要点

Expanding Agent Governance with Unity AI Gateway | Databricks Blog

Expanding Agent Governance with Unity AI Gateway

Control and audit AI agents and coding assistants with unified governance, visibility and guardrails

**Fine-Grained Permissions and Guardrails**

**End-to-End Observability**

**Reliability and Flexibility for Production**

Your compact guide to modern analytics

**Get Started with Unity AI Gateway**

Never miss a Databricks post

Sign up

What's next?

We Care About Your Privacy

Privacy Preference Center

Privacy Preference Center

Cookie List

Fine-Grained Permissions and Guardrails

End-to-End Observability

Reliability and Flexibility for Production

Get Started with Unity AI Gateway