How to Use the Close MCP in Google ADK

Q: How do I give my Google ADK agent access to my Close account?

You'll use the McpToolset class from the Google ADK library. Initialize it with the server URL Vinkius gives you, and then pass it into your LlmAgent's tool list. The agent discovers the Close tools automatically.

Q: Can I pick which Close tools my agent sees?

Yes, the McpToolset constructor in the Google ADK has a toolnames filter. You can provide a list of tool names, like 'getleaddetails', 'listclosetasks', to expose only a specific subset to your agent.

Connect Google ADK agents to your Close CRM. Let Gemini analyze sales data and act on it right from 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 Close MCP to Google ADK

Create your Vinkius account to connect Close 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 Close with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze CRM data with Gemini's context

Pull your entire sales pipeline directly from Close for analysis. Your agent can use `list_close_leads` and `list_close_opportunities` to get a complete dataset. Gemini's long-context window means the agent can reason over thousands of records at once. This is great for spotting trends you'd otherwise miss. You can ask your agent to find all opportunities in a specific stage from a certain region, and it can hold all that context to give you a straight answer. You can even have it pipe the results into BigQuery.

Build pipeline monitors on Google Cloud

Create agents that live inside your Google Cloud project and keep an eye on your sales funnel. With `list_close_pipelines` and `get_opportunity_details`, an agent can track deal progression and flag stalled opportunities. Because it's running on Google's infrastructure, your agent can easily connect to other Google services. For example, it could check an opportunity's status in Close, then trigger a Google Cloud Function if a deal closes.

Connect agents to your Close task list

This MCP Server lets your Google ADK agent see its own to-do list from Close. The `list_close_tasks` tool gives it a starting point for its work. The agent can then use other tools to execute those tasks. This setup works well for building enterprise automation. An agent can pull its assigned tasks, fetch lead details with `get_lead_details`, and use Vertex AI to enrich that data before deciding on the next step. It's all connected.

Setup guide

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

You'll use the `McpToolset` class from the Google ADK library. Initialize it with the server URL Vinkius gives you, and then pass it into your `LlmAgent`'s tool list. The agent discovers the Close tools automatically.

Yes. Your agent can fetch data from Close using tools from this MCP Server, like `list_close_leads`. Then, it can use native Google Cloud tools within the same agent to process that data and insert it into a BigQuery table.

The connection is a standard, low-latency HTTP stream. Since your agent is likely running on Google Cloud, network latency to the Vinkius MCP endpoint will be minimal. The performance bottleneck will usually be the model's inference time, not the tool call.

Yes, the `McpToolset` constructor in the Google ADK has a `tool_names` filter. You can provide a list of tool names, like `['get_lead_details', 'list_close_tasks']`, to expose only a specific subset to your agent.

Data privacy is handled at multiple levels. Your agent's requests for lead and opportunity records are isolated within the Vinkius zero-trust environment. Plus, you control access through your Google Cloud project's own IAM policies, defining which services or principals can invoke the agent.

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