How to Use the Klaviyo MCP in Google ADK

Q: How do I connect the Klaviyo MCP Server to Google ADK?

Create an McpToolset using your connection URL. Pass that toolset to the tools array when defining your LlmAgent.

Q: Can I restrict which Klaviyo tools my Google ADK agent uses?

You can filter the exposed functions using the toolnames parameter. Pass a list of safe tools to prevent the agent from modifying records.

Feed data from this Klaviyo MCP Server straight into Google ADK so Gemini agents can build segments using BigQuery context.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Klaviyo MCP to Google ADK

Create your Vinkius account to connect Klaviyo 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 Klaviyo with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync Profiles with Gemini Agents

The `create_profile` and `list_profiles` tools let your Google ADK agent manage subscriber records directly. You can pass a user's purchase history from BigQuery into the context window, and Gemini will decide if they need a new profile entry. It handles the API call natively. Long-context reasoning changes how you handle bulk updates. You can dump thousands of rows of customer behavior into the prompt and ask the agent to tag them using `list_tags`. The model parses the massive dataset and executes the correct updates one by one.

Trigger Flows from Google Cloud

Agents trigger marketing automation by interacting with the `list_automated_flows` tool. When an anomaly triggers an alert in Vertex AI, the agent checks available flows to find the right response sequence. It then pushes the user into that flow without human intervention. You restrict what the agent can touch using the `tool_names` filter. If a specific agent should only read data, you limit it to `list_metrics` and `list_campaigns`. This prevents a rogue process from accidentally launching a massive email blast.

Monitor Pipelines via MCP Server

Auditing your event pipelines requires the `list_webhooks` tool to see where your data is flowing. The agent queries the active endpoints and compares them against your known Google Cloud architecture. If a webhook points to a dead server, the agent flags it. Setup takes two lines of code using `McpToolset`. You point `StreamableHttpServerParameters` at the Vinkius URL and attach it to your `LlmAgent`. Gemini automatically understands the schema and starts pulling real-time marketing data.

Setup guide

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

Create an `McpToolset` using your connection URL. Pass that toolset to the `tools` array when defining your `LlmAgent`.

You can filter the exposed functions using the `tool_names` parameter. Pass a list of safe tools to prevent the agent from modifying records.

Gemini's massive token context window absorbs heavy JSON payloads from the metrics endpoint without truncating. The agent reads the entire historical dataset to spot trends before generating a summary.

Yes. The integration acts as a standard toolset within the Google ADK ecosystem. Your agents can cross-reference Vertex AI predictions with current marketing lists.

The integration handles raw purchase events and email addresses through a zero-trust architecture. Authentication happens strictly via your single endpoint token, and the Vinkius sandbox destroys the execution environment immediately after the request completes.

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