How to Use the Customerly MCP in Google ADK

Q: How do I limit Customerly MCP tool access in the Google ADK?

Use the optional toolnames filter when initializing the toolset. This restricts the agent to specific actions like reading chats while blocking deletions.

Connect Customerly to the Google ADK and let Gemini agents analyze millions of chat conversations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customerly MCP to Google ADK

Create your Vinkius account to connect Customerly 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 Customerly with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process massive support histories

The `list_conversations` MCP tool dumps your entire chat backlog into Gemini's massive context window. Enterprise agents on Google Cloud can read thousands of user interactions at once to identify churn signals. Digging into a specific thread requires the `get_conversation` endpoint. Your agent pulls the exact back-and-forth dialogue and cross-references it with product usage data stored in BigQuery.

Automate CRM updates via Google ADK

Firing the `create_update_user` tool keeps your marketing platform synced with your data warehouse. When a Vertex AI pipeline scores a customer's churn risk, the agent updates their profile attributes immediately. Managing prospects works the same way with `create_update_lead`. You pass the email address and any custom fields directly through the HTTP transport for this MCP connection. This eliminates the need for brittle third-party sync scripts.

Segment users with dynamic tags

Executing `add_tag` lets your agent organize contacts based on complex reasoning. If Gemini detects frustration in a ticket, it applies an at-risk label so your success team can intervene. Reversing that action uses the `remove_tag` tool. Once the customer renews their contract, the system strips the warning label. You can filter which of these operations are exposed using the tool_names parameter.

Setup guide

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

Import McpToolset from the google-adk package. Pass your Vinkius URL into StreamableHttpServerParameters and hand the toolset to your LlmAgent.

It reads them perfectly. The agent calls the conversation endpoints and feeds the text directly into Gemini for analysis.

The server itself just handles the CRM API. Your Google ADK agent acts as the bridge, pulling metrics from BigQuery and pushing the resulting insights into user profiles.

Use the optional tool_names filter when initializing the toolset. This restricts the agent to specific actions like reading chats while blocking deletions.

Lead emails and chat logs pass through a zero-trust architecture. The Vinkius endpoint token authenticates the request, and the isolated sandbox immediately wipes all memory after processing.

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