How to Use the Northbeam MCP in Google ADK

Q: How can I use Google ADK to get Northbeam data into BigQuery?

Your agent uses the createdataexport tool to generate a report in Northbeam. Once getexportstatus shows it's complete, your agent can download the data and use other Google Cloud tools to load it into a BigQuery table.

Q: Can I filter which Northbeam tools my Google ADK agent sees?

Yes. When you initialize the McpToolset for the Google ADK, you can pass a toolnames filter. This lets you expose only specific Northbeam actions, like createdataexport and getexportstatus, to your agent.

Q: How do I manage scheduled Northbeam reports with a Google ADK agent?

Your agent can call listscheduledexports to review all automated reports. This is useful for building a dashboard in Looker Studio that not only shows attribution data but also confirms your Northbeam data pipelines are healthy.

Run Northbeam attribution analysis at enterprise scale with Google ADK and Gemini's long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Northbeam MCP to Google ADK

Create your Vinkius account to connect Northbeam 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 Northbeam with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Northbeam Data in BigQuery

Your Gemini-powered agent can now pull marketing data directly into your Google Cloud environment. It uses `create_data_export` to get the exact metrics you need from Northbeam, like attributed revenue and spend. Once the export is ready—which your agent checks with `get_export_status`—the real work begins. The Google ADK makes it simple to pipe that data straight into a BigQuery table for large-scale analysis, joining it with your existing enterprise data.

Build Complex Reports with the Google ADK

Gemini's massive context window lets your agent reason over complex marketing strategies. It can review all available `list_attribution_models` and `list_breakdowns` from Northbeam in a single prompt. Your agent can then formulate a multi-step plan: first, check account settings with `get_account_info`, then decide on a report structure, and finally execute it. This moves beyond simple Q&A into true strategic automation inside your GCP project.

Automate Northbeam Export Schedules

Use your agent to manage your reporting schedule. It can get a list of all current jobs with `list_scheduled_exports` and even check on webhook configurations with `list_webhooks`. This integrates Northbeam's operations directly into your Google Cloud workflow. You could have a Cloud Function trigger your agent to verify that a daily Northbeam export ran correctly, creating a robust, automated reporting pipeline via this MCP Server.

Setup guide

Set up Northbeam 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 Northbeam 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="Northbeam_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Northbeam 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 Northbeam. 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 Northbeam 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 Northbeam MCP in Google ADK

Your agent uses the `create_data_export` tool to generate a report in Northbeam. Once `get_export_status` shows it's complete, your agent can download the data and use other Google Cloud tools to load it into a BigQuery table.

Absolutely. With Google ADK, you can load all available models from `list_attribution_models` and breakdowns from `list_breakdowns` into the context. This lets your Gemini agent reason about the best reporting strategy for Northbeam in one go.

Yes. When you initialize the `McpToolset` for the Google ADK, you can pass a `tool_names` filter. This lets you expose only specific Northbeam actions, like `create_data_export` and `get_export_status`, to your agent.

Your agent can call `list_scheduled_exports` to review all automated reports. This is useful for building a dashboard in Looker Studio that not only shows attribution data but also confirms your Northbeam data pipelines are healthy.

The connection uses a unique Vinkius token, and the server instance is isolated. It only processes Northbeam attribution metrics and identifiers. Since you use Google ADK, your agent's logic and the data it handles are all contained within your own GCP project's security boundaries.

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