How to Use the Clari MCP in Google ADK

Q: How do I connect Google ADK to my Clari account?

You'll use the McpToolset from the google-adk library, pointing it to your unique Vinkius URL for the MCP Server. Pass that toolset to your agent, and it will discover all the available Clari tools.

Let your Google ADK agents act on your Clari sales data. Connect Gemini's long-context reasoning to your live revenue pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clari MCP to Google ADK

Create your Vinkius account to connect Clari 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 Clari with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Forecasts with Gemini

Pull years of forecast history from Clari and feed it directly into a Gemini model. The `list_clari_forecasts` and `list_clari_time_periods` tools give you the raw data. Google ADK lets your agent hold all that context to find trends your team might have missed. This gets really powerful when you combine it with your other data. You can have your agent pull Clari forecast data, cross-reference it with customer usage stats from BigQuery, and then generate a new projection. It's all happening inside your Google Cloud environment.

Your Clari MCP Server on GCP

Build agents that give your sales team instant answers. An agent using `list_revenue_opportunities` and `get_opportunity_revenue_details` can answer questions like 'What are the top 5 deals in the pipeline for ACME Corp?'. It's faster than logging into another system. You set this up by wrapping the Vinkius URL in an `McpToolset` and passing it to your `LlmAgent`. Google ADK is built for enterprise use cases on GCP, so this integration fits right into your existing infrastructure. You can even filter the tools exposed to the agent for tighter control.

Run Compliance and Audit Workflows

Automate your compliance checks. An agent can periodically run `list_clari_audit_logs` to check for unusual activity, like a deal's value changing right before quarter-end. It can also use `list_clari_users` to confirm who made the change. This MCP Server acts as a secure bridge between Google Cloud and Clari. Your ADK agent makes a simple call, and Vinkius handles the connection to Clari. It's a clean way to give your cloud-native agents access to SaaS data without managing credentials or custom APIs.

Setup guide

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

You'll use the `McpToolset` from the `google-adk` library, pointing it to your unique Vinkius URL for the MCP Server. Pass that toolset to your agent, and it will discover all the available Clari tools.

Yes. That's a great use case for it. You can use a tool like `list_clari_forecasts` to pull extensive historical data from Clari and have your Google ADK agent analyze it all in a single prompt.

Your Google ADK agent runs in your GCP environment. It makes a direct, secure call to the Vinkius MCP Server, which then fetches data from Clari. The data flows from Clari, through the Vinkius sandbox, to your agent.

Absolutely. Your Google ADK agent can call a Clari tool like `list_revenue_opportunities`, get the data, and then use a separate BigQuery tool to insert it into a table. It's a perfect way to build ETL pipelines managed by an agent.

The agent gets access to your Clari revenue intelligence data, including opportunities, accounts, user lists, and forecast submissions. Every request goes through the Vinkius MCP Server, a zero-trust, ephemeral instance, and data is only passed through, not stored.

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