How to Use the Customer.io MCP in Google ADK

Q: How do I configure Customer.io with Google ADK?

Initialize an McpToolset using the StreamableHttpServerParameters and your Vinkius URL. Pass this directly into your LlmAgent tools array. The Gemini model immediately recognizes the MCP Server capabilities.

Q: Can Google ADK analyze Customer.io campaign performance?

The agent pulls metrics directly via getcampaignperformance. Thanks to Gemini's massive context window, you compare these stats against massive BigQuery datasets in a single prompt.

Q: How do I restrict which tools Google ADK can use?

Apply the optional toolnames filter when setting up your toolset. This lets you expose read-only tools like listnewsletters while blocking execution commands like dispatchbroadcast.

Q: Can my Google ADK agent read Customer.io audience segments?

Yes, it calls listaudiencesegments to view your groupings. It drills down further using listsegmentmembers to see exactly who belongs to each list.

Give Google ADK agents the power to read Customer.io segments and trigger broadcasts across your Gemini ecosystem.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customer.io MCP to Google ADK

Create your Vinkius account to connect Customer.io 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 Customer.io with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync Customer.io segments with Google ADK

Enterprise agents need to bridge your data warehouse and your messaging platform. Adding this MCP Server to your Google ADK setup lets Gemini read `list_audience_segments` alongside your BigQuery tables. The agent cross-references your internal analytics with actual mailing lists. Long-context reasoning makes massive datasets manageable. You pull thousands of users via `list_customers` and feed them into the 1M+ token window. The model analyzes behavior patterns before deciding who gets the next email.

Trigger campaigns from Vertex AI

Your Google Cloud infrastructure acts on user behavior directly. When Vertex AI detects a churn risk, the agent fires `dispatch_broadcast` to send a targeted re-engagement offer. You pass the `McpToolset` to your `LlmAgent` and the integration is live. Checking what is currently running takes seconds. The agent runs `list_active_campaigns` and `list_scheduled_broadcasts` to ensure it avoids overwhelming users with duplicate messaging. Everything stays within your existing GCP deployment powered by this MCP Server.

Fetch profiles and send individual emails

Single users often need targeted messages based on specific app activity. The agent grabs their exact history using `get_customer_details` and immediately fires `send_transactional_email`. You control exactly which tools are exposed by applying a `tool_names` filter in the toolset configuration. Reviewing past communications prevents embarrassing mistakes. Gemini uses `list_transactional_messages` to see if a password reset already went out. Checking `get_connection_status` keeps the agent aware of API health before it attempts any new sends.

Setup guide

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

Initialize an `McpToolset` using the `StreamableHttpServerParameters` and your Vinkius URL. Pass this directly into your `LlmAgent` tools array. The Gemini model immediately recognizes the MCP Server capabilities.

The agent pulls metrics directly via `get_campaign_performance`. Thanks to Gemini's massive context window, you compare these stats against massive BigQuery datasets in a single prompt.

Apply the optional `tool_names` filter when setting up your toolset. This lets you expose read-only tools like `list_newsletters` while blocking execution commands like `dispatch_broadcast`.

Yes, it calls `list_audience_segments` to view your groupings. It drills down further using `list_segment_members` to see exactly who belongs to each list.

Data like email addresses and behavioral histories flow through an ephemeral, zero-trust sandbox. The Google ADK agent only holds the `get_customer_details` payload in memory during the active session, leaving no permanent traces on the Vinkius edge network.

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