How to Use the Google Contacts MCP in Google ADK

Q: How do I register Google Contacts tools inside a Google ADK agent?

You instantiate McpToolset with your Vinkius HTTP URL and pass it to your LlmAgent constructor. The framework automatically registers the 9 contact management tools and exposes them to Gemini's function calling engine.

Q: How do I limit my Google ADK agent to only read Google Contacts?

You use the toolnames filter when initializing your McpToolset to only expose getcontact, listcontacts, and searchcontacts. This prevents your agent from calling write tools like deletecontact.

Connect Google Contacts directly to your Google ADK pipelines to enrich enterprise Gemini agents with real-time address book data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Contacts MCP to Google ADK

Create your Vinkius account to connect Google Contacts 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 Google Contacts with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Contextual address book lookups in Google ADK

`search_contacts` lets your Gemini agent query your directory using natural language queries directly from your BigQuery datasets. The agent matches unstructured database names against actual Google profiles to clean up dirty data. With Gemini's million-token context window, the ADK can pull hundreds of contacts via `list_contacts` and analyze relationship networks in a single prompt. This lets you run complex networking analyses without pagination bottlenecks.

Automate contact groups using this MCP Server

`create_contact_group` and `list_contact_groups` allow your enterprise agent to dynamically segment your network based on active projects. The agent reads client updates from Vertex AI and organizes contacts into clean, labeled folders. This automated grouping makes it easy to broadcast updates or manage mailing lists without manual sorting. Your agent handles the structural organization while you focus on the actual client communication.

Exact contact synchronization and details

`get_contact` and `update_contact` ensure your agent always works with the latest phone numbers, emails, and notes. The agent gets the current contact payload, updates the fields, and writes them back using the required etag. By using the Google ADK toolset configuration, you can plug this MCP Server into specific service accounts. This protects your corporate directory while giving your agent the exact tools it needs to keep data fresh.

Setup guide

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

You instantiate `McpToolset` with your Vinkius HTTP URL and pass it to your `LlmAgent` constructor. The framework automatically registers the 9 contact management tools and exposes them to Gemini's function calling engine.

Yes, your agent can query BigQuery for stale records and then call `update_contact` to refresh them. This is a common pattern for keeping your sales directory synchronized with enterprise database tables.

Yes, the SDK supports both transport types depending on your hosting environment. For serverless deployments on Google Cloud, we recommend using the HTTP transport to connect to our hosted MCP server.

You use the `tool_names` filter when initializing your `McpToolset` to only expose `get_contact`, `list_contacts`, and `search_contacts`. This prevents your agent from calling write tools like `delete_contact`.

Your contact profiles and group labels are processed in an isolated memory space and never written to persistent storage. This MCP Server handles authentication via a single endpoint token, routing API payloads directly between Google Cloud and the People API.

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