---
title: "Meta’s ads MCP server comes to Databricks: Put your customer intelligence to work in advertising campaigns"
description: "Meta’s ads MCP server, now in Databricks Marketplace, connects Meta Ads Manager tools with enterprise data through Genie for natural language campaign management. The server uses the open MCP standard to expose over 25 tools across the campaign lifecycle including creating campaigns, adjusting budgets, defining audiences, and pulling performance data. Marketers can prompt Genie One to use business data like churn scores and gross margins, for example identifying high-value customers at risk of leaving and launching a retention campaign with an $8,000 daily budget. Governance is enforced server-side: Databricks administrators control access via Unity Catalog while Meta advertisers set rules in Business Settings that block actions like budget increases over 20%, with every tool call checked before execution. The integration builds on the Meta Conversions API partnership, letting agents combine signal diagnostics with Databricks models to put customer intelligence directly into campaign operations and execution."
---

# Meta’s ads MCP server comes to Databricks: Put your customer intelligence to work in advertising campaigns

[Databricks](https://yomu.fyi/company/databricks) · Katy Yuan, Jen McNamee, Rohith Bhatia · Oct 6, 2026

**Type:** Announcement

## Summary

Meta’s ads MCP server, now in Databricks Marketplace, connects Meta Ads Manager tools with enterprise data through Genie for natural language campaign management. The server uses the open MCP standard to expose over 25 tools across the campaign lifecycle including creating campaigns, adjusting budgets, defining audiences, and pulling performance data. Marketers can prompt Genie One to use business data like churn scores and gross margins, for example identifying high-value customers at risk of leaving and launching a retention campaign with an $8,000 daily budget. Governance is enforced server-side: Databricks administrators control access via Unity Catalog while Meta advertisers set rules in Business Settings that block actions like budget increases over 20%, with every tool call checked before execution. The integration builds on the Meta Conversions API partnership, letting agents combine signal diagnostics with Databricks models to put customer intelligence directly into campaign operations and execution.

## Context

Enterprise advertisers often have customer intelligence in Databricks (churn models, LTV scores, attribution data) but rely on manual handoffs like CSV exports or custom integrations to inform Meta campaign decisions. This release follows the Meta Conversions API on Databricks Marketplace and aims to bridge that gap by connecting governed business data directly with Meta’s advertising tools.

## Approach / What changed

The ads MCP server from Meta, available in Databricks Marketplace, uses the open Model Context Protocol to expose over 25 advertising tools. It connects to Databricks’ Genie One, allowing marketers to use natural language to combine Meta campaign data with governed business data. Governance is enforced server-side through Unity Catalog for access control and Meta Business Settings for rule enforcement on tool calls.

## Takeaways

- The ads MCP server exposes over 25 tools across the campaign lifecycle, including creating campaigns, adjusting budgets, defining audiences, and pulling performance data.
- Governance is enforced server-side: Databricks administrators control access via Unity Catalog, and Meta advertisers set rules in Business Settings that block actions like budget increases over 20%, with every tool call checked before execution.
- Marketers can use natural language in Genie One to combine business data (e.g., churn scores, gross margins) with Meta campaign data, enabling actions like launching a retention campaign with a specific daily budget.

## FAQ

### How does governance work when an AI agent manages Meta ad campaigns?

Databricks administrators control access through Unity Catalog, and Meta advertisers set rules in Business Settings that block actions like budget increases over 20%. The server checks every tool call against those rules before executing, and the same rules can be managed through the Marketing API for large-scale accounts.

### What tools does the ads MCP server expose?

The server exposes over 25 tools across the campaign lifecycle, including creating campaigns and ad sets, changing budgets and bids, defining audiences, managing creative and catalogs, pulling performance data, and diagnosing signal quality.

### How can marketers use their own data in campaign decisions?

Marketers can prompt Genie One to use business data like churn scores or gross margins to inform campaign decisions, for example by asking it to identify high-value customers at risk of leaving and launch a retention campaign with an $8,000 daily budget.

**Tags:** [Advertising](https://yomu.fyi/topic/advertising), [AI Agents](https://yomu.fyi/topic/ai-agents), [Databricks](https://yomu.fyi/topic/databricks), [MCP](https://yomu.fyi/topic/mcp), [Meta](https://yomu.fyi/topic/meta)

- Source: [Databricks](https://www.databricks.com/blog/meta-ads-mcp-databricks)
- Source URL: https://www.databricks.com/blog/meta-ads-mcp-databricks
- Ingested by Yomu: 2026-10-06T15:00:07.542Z

[Read original post](https://www.databricks.com/blog/meta-ads-mcp-databricks)