How to Use the Clientify MCP in Google ADK

Q: How do I connect Clientify to a Google ADK agent?

You'll use the McpToolset class from the ADK, pointing it to your Vinkius MCP server URL. Then you just pass that toolset into your LlmAgent constructor. The ADK handles the rest.

Q: Can I restrict which Clientify tools my Google ADK agent can access?

Yes, the McpToolset constructor has a toolnames filter. You can pass it a list of strings to restrict which tools from the Clientify MCP server the agent can see.

Connect Google's Gemini agents to your Clientify CRM. Build enterprise-scale automations on Google Cloud with the ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clientify MCP to Google ADK

Create your Vinkius account to connect Clientify 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 Clientify with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Clientify Data into BigQuery

The `list_clientify_contacts` and `list_clientify_companies` tools let your ADK agent pull your entire CRM roster. It can then fetch specifics on deals and activities using `list_sales_deals` and `list_crm_activities`. Because the Google ADK is native to the Google Cloud ecosystem, your agent can take that data and pipe it directly into a BigQuery table for analysis. This is how you build a real-time CRM analytics pipeline without writing a bunch of custom ETL scripts.

Analyze Sales Pipelines with Gemini

This MCP Server exposes your sales process through tools like `list_sales_pipelines` and `get_deal_details`. Your agent can pull all this information into its context window. With a Gemini model and its massive context window, the agent can hold your entire sales pipeline in memory. It can then reason about deal velocity, identify bottlenecks, and summarize findings, all in a single pass. You're not just fetching data; you're analyzing it at scale.

Build Enterprise Agents with the Google ADK

Your agent can use `get_my_clientify_profile` to verify its identity before acting on your CRM. The Google ADK lets you define specific tools for your agent, so you can create a specialized agent that only has permission to read company data with `list_clientify_companies`, for example. This is perfect for enterprise environments where you need strict controls. Combine the ADK's tool filtering with Google Cloud's IAM roles to build agents that are both powerful and compliant. It's about giving the agent just enough permission to do its job.

Setup guide

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

You'll use the `McpToolset` class from the ADK, pointing it to your Vinkius MCP server URL. Then you just pass that toolset into your `LlmAgent` constructor. The ADK handles the rest.

Yes. The ADK is built for Gemini models. Your agent can fetch deal information from Clientify using the MCP tools and then use Gemini Pro's long-context capabilities to analyze the entire dataset in one go.

The tight integration with Google Cloud is the main reason. If your data warehouse is BigQuery or you use Vertex AI for model management, the ADK is the most direct path to connect your Clientify data to those services.

Yes, the `McpToolset` constructor has a `tool_names` filter. You can pass it a list of strings to restrict which tools from the Clientify MCP server the agent can see.

Your CRM data, including contacts and sales deals, is accessed via an authenticated, point-to-point connection. The Vinkius MCP server runs in a zero-trust environment and doesn't persist any of your data. Think of it as a secure, temporary proxy for your agent's requests.

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