How to Use the Facebook Ads MCP in Google ADK

Q: How do I set up the Facebook Ads MCP Server in Google ADK?

Use the McpToolset class with StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset into your LlmAgent configuration. This instantly exposes all 12 Meta tools to your Gemini model.

Q: Does Google ADK support selective tool exposure for Facebook Ads?

Yes. You can use the optional toolnames filter when initializing your toolset. This allows you to expose only listads and getaddetails while blocking write operations.

Q: How does Gemini's long context benefit Facebook Ads management?

You can pass the complete output of listcampaigns and getinsights for your entire account. Gemini analyzes the entire structure at once, finding complex correlations that smaller models fail to process.

Connect your Facebook Ads data to BigQuery and control campaigns using Gemini models via the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Facebook Ads MCP to Google ADK

Create your Vinkius account to connect Facebook Ads to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Facebook Ads with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Cross-channel analysis using Gemini and BigQuery

Stop looking at Meta ads in a vacuum. By using this MCP Server alongside Google Cloud, your agent can pull live performance data using `get_insights` and compare it directly with your internal SQL warehouse tables. Gemini's massive context window lets you feed months of historical campaign data from `list_campaigns` alongside your CRM database. The agent can spot attribution gaps that standard dashboards miss entirely.

Enterprise-scale campaign pruning via Google ADK

Large-scale ad accounts are too complex for manual oversight. This integration lets you build enterprise agents that monitor hundreds of live ad sets. Use `list_ad_sets` to map your entire structure, then let Gemini determine which ones are wasting budget. When an ad set fails to hit your target metrics, the agent uses `update_ad_set_status` to pause it. Because it runs on Google Cloud, you can trigger these checks via Cloud Functions on a cron job.

Granular ad inspection with long-context reasoning

Feed entire ad creative histories into your agent. By configuring this MCP integration across your entire account, you can analyze copy, targeting, and spend patterns in a single prompt. The agent uses this deep context to flag creative fatigue. Instead of guessing when to swap ads, you get clear recommendations backed by hard spend data from `get_ad_account_info`.

Setup guide

Set up Facebook Ads MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Facebook Ads tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Facebook Ads_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Facebook Ads tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Facebook Ads. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Facebook Ads now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Facebook Ads MCP in Google ADK

Use the `McpToolset` class with `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass this toolset into your `LlmAgent` configuration. This instantly exposes all 12 Meta tools to your Gemini model.

Yes, if you store offline conversions in BigQuery. Your agent can query those tables, compare them with live metrics from `get_insights`, and then call `update_campaign_status` to manage your budget.

Yes. You can use the optional `tool_names` filter when initializing your toolset. This allows you to expose only `list_ads` and `get_ad_details` while blocking write operations.

You can pass the complete output of `list_campaigns` and `get_insights` for your entire account. Gemini analyzes the entire structure at once, finding complex correlations that smaller models fail to process.

Your Meta developer credentials and system user tokens are held in Vinkius's zero-trust sandbox. The Google ADK agent only interacts with the standardized MCP interface, meaning your raw API keys never enter your Google Cloud runtime environment.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript