How to Use the Kustomer MCP in Google ADK

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

You instantiate an McpToolset with your Vinkius server URL. Then you pass that toolset into your LlmAgent constructor. The ADK handles the tool discovery from there.

Q: How can I limit which Kustomer tools my Google ADK agent can access?

When you create the McpToolset, you can pass an optional toolnames filter. This lets you expose only a specific subset of tools, like getconversationdetails, while hiding others.

Link Google's Gemini agents to Kustomer and run analytics on support data directly within your Google Cloud environment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kustomer MCP to Google ADK

Create your Vinkius account to connect Kustomer 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 Kustomer with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Kustomer Data in BigQuery

Use a Gemini agent to pull raw support data out of Kustomer. The agent can `list_kustomer_customers` and then iterate through them, using `list_support_conversations` to grab every ticket. It's a straight shot from Kustomer to your cloud environment. The ADK's native integration with Google Cloud means you can pipe this data directly into a BigQuery table. From there, you can run large-scale analysis or train a custom Vertex AI model on your own support history. This MCP server is the bridge.

Long-Context Conversation Summaries

Gemini's huge context window changes the game for support. Your agent can fetch a customer's entire history by calling `get_customer_profile` and then `search_kustomer_timeline` with a wide date range. You get everything. Instead of just getting the last few messages, your agent can hold years of conversation history in its context. It can then generate summaries, identify recurring issues, or spot churn risks with a level of understanding that was impossible before.

Build Enterprise Bots with your Google ADK

This MCP server gives your Google ADK agent the tools to act like a real support team member. It can `list_support_queues` to understand your team structure and `list_kustomer_agents` to see who is available. Because you're in the Google ecosystem, you can connect this to Pub/Sub for event-driven triggers or Cloud Functions for serverless actions. An incoming Kustomer ticket can trigger an agent that diagnoses the issue and prepares a draft response, all within your GCP project.

Setup guide

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

You instantiate an `McpToolset` with your Vinkius server URL. Then you pass that toolset into your `LlmAgent` constructor. The ADK handles the tool discovery from there.

Yes, that's a primary use case. Your Google ADK agent can use `list_kustomer_customers` and `list_support_conversations` to fetch the data, then use other tools to push it into BigQuery for analysis.

Yes. The tool descriptions are designed to be understood by the model. When you ask it to 'find all of John Doe's tickets,' it knows to use `get_customer_profile` and then `list_support_conversations`.

When you create the `McpToolset`, you can pass an optional `tool_names` filter. This lets you expose only a specific subset of tools, like `get_conversation_details`, while hiding others.

The server interacts with customer profiles, their conversation timelines, and internal queue/agent lists from your Kustomer account. All data is passed through a zero-trust, ephemeral Vinkius sandbox, and your Kustomer credentials are never exposed to the client.

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