How to Use the Braze MCP in Google ADK

Q: How does Google ADK handle large user exports from Braze?

The agent uses exportuserids to retrieve profile details. Because Google ADK supports Gemini's massive context window, you can feed these user profiles directly into the model for bulk analysis.

Q: Is there a way to limit which Braze tools Google ADK can access?

Yes, you can use the toolnames filter in your Google ADK setup to restrict the agent. For example, you can expose listcampaigns but block deleteuser to prevent accidental deletions.

Connect your Google ADK agents to Braze to trigger campaigns and track users using 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 Braze MCP to Google ADK

Create your Vinkius account to connect Braze 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 Braze with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Braze campaigns from Google ADK pipelines

The `trigger_campaign` tool initiates API-driven campaigns, and `trigger_canvas` starts specific customer journeys. By exposing these tools to your Google ADK pipeline, your Gemini-powered agents can launch targeted messaging campaigns based on real-time triggers. Because Gemini handles huge context windows, your agent can analyze hours of user activity logs from Google Cloud before deciding to call `trigger_canvas`. This setup connects your marketing engine directly to your enterprise data warehouse without writing custom middleware.

Sync BigQuery data using this MCP Server

The `track_user` tool updates customer traits and logs events, while `export_user_ids` pulls profile data for specific cohorts. Your Google ADK agent uses these tools to bridge the gap between your marketing platform and Google Cloud data sources. When your agent identifies a segment change in BigQuery, it uses this MCP Server to push those updates to the corresponding profiles. This ensures your marketing segments stay updated based on actual database changes, not just web clicks.

Map active journeys inside Google ADK

The `list_canvases` tool fetches all active user journeys, and `get_canvas_details` retrieves the step-by-step configuration of a specific journey. Your Google ADK agent calls these tools over the MCP Server to map out how customers move through your active marketing flows. Gemini's long-context capabilities allow the agent to read the entire JSON structure returned by `get_campaign_details` to verify if a user has already received a specific message. This prevents the agent from triggering duplicate emails or push notifications.

Setup guide

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

Yes, your agent can query BigQuery, analyze the results, and then call `trigger_campaign` to message those users. This lets you run complex database-driven marketing loops.

The agent uses `export_user_ids` to retrieve profile details. Because Google ADK supports Gemini's massive context window, you can feed these user profiles directly into the model for bulk analysis.

Yes, you can use the tool_names filter in your Google ADK setup to restrict the agent. For example, you can expose `list_campaigns` but block `delete_user` to prevent accidental deletions.

The server runs in a secure, hosted environment on Vinkius. Your Google ADK agent connects via a single HTTP endpoint, keeping your API keys hidden from the client-side code.

All user attributes, external IDs, and event tracking payloads are processed in transit inside temporary sandbox environments. No customer profile data is cached or saved on Vinkius, maintaining direct security between Google Cloud and your marketing endpoints.

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