How to Use the Gmail MCP in Google ADK

Q: How do I configure Google ADK to search Gmail messages?

You register the Gmail MCP Server parameters inside the McpToolset constructor. Your Gemini model then uses listgmailmessages to run search queries directly from your Python script.

Q: Can my Google ADK agent delete Gmail messages?

Yes, your Google ADK agent can call trashgmailmessage to move junk emails to the trash folder. You can also run untrashgmailmessage to recover them if needed.

Q: Does the Google ADK integration support standard Gmail search operators?

Yes, the listgmailmessages tool accepts the standard query parameter "q" through the Google ADK. Your agent can search by dates, subjects, or attachment types exactly like you do in the web app.

Q: How do I restrict my cloud agent to specific tools?

You pass a list of allowed tool names to the McpToolset initialization. This limits the Google ADK agent to safe actions like listunreademails while blocking destructive tools.

Connect Gmail to your Google Cloud data pipelines using Google ADK and Gemini long-context MCP tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gmail MCP to Google ADK

Create your Vinkius account to connect Gmail 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 Gmail with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process entire Gmail threads with Google ADK.

The `get_thread_details` tool pulls complete email conversations directly into your Google ADK agent. Because Gemini models handle massive token limits, you can feed entire multi-year threads into a single prompt. This integration allows your Google ADK agent to cross-reference inbox conversations with your BigQuery datasets. The model reads the output of `list_gmail_messages` and matches sender addresses against CRM tables.

Verify connections with the Gmail MCP Server.

The `verify_api_connection` tool checks that your Google ADK agent has active access to the mailbox. If a token expires or a cloud policy changes, this MCP tool flags the failure before your pipeline attempts to read data. This pre-flight check keeps enterprise pipelines running smoothly on Google Cloud. Your agent runs the check, verifies the `get_gmail_profile` response, and then starts processing incoming inquiries.

Organize Google ADK pipelines with custom labels.

The `modify_message_labels` tool applies or removes labels to route incoming emails to specific processing queues. Your Google ADK agent calls `list_unread_emails` to find new work, processes it, and marks it sorted. This automation runs natively alongside your other Vertex AI tools. By updating labels, your agent signals to downstream Google Cloud systems that an email has been analyzed.

Setup guide

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

You register the Gmail MCP Server parameters inside the `McpToolset` constructor. Your Gemini model then uses `list_gmail_messages` to run search queries directly from your Python script.

Yes, your Google ADK agent can call `trash_gmail_message` to move junk emails to the trash folder. You can also run `untrash_gmail_message` to recover them if needed.

Yes, the `list_gmail_messages` tool accepts the standard query parameter "q" through the Google ADK. Your agent can search by dates, subjects, or attachment types exactly like you do in the web app.

You pass a list of allowed tool names to the `McpToolset` initialization. This limits the Google ADK agent to safe actions like `list_unread_emails` while blocking destructive tools.

Your Gmail profile and message contents are protected by Vinkius's zero-trust MCP architecture. All data decrypted during tool execution is isolated in a temporary V8 sandbox and never written to persistent logs.

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