How to Use the AgentMail MCP in Google ADK

Q: How do I set up AgentMail with my Google ADK agent?

You'll use the McpToolset class. Just pass your unique Vinkius server URL into StreamableHttpServerParameters. The ADK handles the connection, exposing tools like sendmessage to your LlmAgent.

Q: Can my agent on Google ADK filter which AgentMail tools it uses?

Yes. The McpToolset constructor in the Google ADK has a toolnames filter. You can use it to expose only a subset of the AgentMail tools, for instance, only allowing listthreads and getthread for a read-only agent.

Q: Can a Gemini agent use AgentMail with Google ADK to summarize long email chains?

That's a primary strength. The agent would use getthread to fetch all messages, and thanks to Gemini's long-context capabilities, it can analyze the entire conversation at once to provide a concise summary.

Connect your Google ADK agents to email. Let them read, send, and manage messages right from Google Cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgentMail MCP to Google ADK

Create your Vinkius account to connect AgentMail 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 AgentMail with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Email Inboxes for Your Gemini Agents

Your Gemini-powered agents can now have their own email addresses. The `create_inbox` tool lets an agent generate a new inbox, and `list_inboxes` shows all the addresses it has access to. This is perfect for enterprise workflows on Google Cloud. For example, an agent monitoring BigQuery for anomalies can create a temporary inbox with `create_inbox` to notify a specific team, then `delete_inbox` when the issue is resolved.

Full-Thread Email Analysis

Don't just read one email, read the whole story. Your agent can use `list_threads` to get an overview of an inbox, then `get_thread` to pull every single message in a conversation. With the Google ADK and Gemini's massive context window, you can feed an entire, complex email thread into the model at once. This lets the agent understand the full history before deciding to use `reply_to_message` or `forward_message`. No more out-of-context replies.

Your Google ADK MCP Server for Email

Sending email is now a native tool for your agent. It just calls `send_message` with the content. Need to reply? `reply_to_message` handles it. Integrate this with your other Google Cloud tools. A Vertex AI pipeline can trigger an agent to `get_attachment` from an email, process the file, and then store the results back in a BigQuery table. The AgentMail MCP Server acts as the simple email bridge for your complex cloud logic.

Setup guide

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

You'll use the `McpToolset` class. Just pass your unique Vinkius server URL into `StreamableHttpServerParameters`. The ADK handles the connection, exposing tools like `send_message` to your LlmAgent.

Yes. The `McpToolset` constructor in the Google ADK has a `tool_names` filter. You can use it to expose only a subset of the AgentMail tools, for instance, only allowing `list_threads` and `get_thread` for a read-only agent.

That's a primary strength. The agent would use `get_thread` to fetch all messages, and thanks to Gemini's long-context capabilities, it can analyze the entire conversation at once to provide a concise summary.

Yes, that's the point. AgentMail gives your agent email capability. The Google ADK lets it talk to services like BigQuery and Vertex AI. You can build workflows that cross all these services.

AgentMail processes the contents of your emails, including message bodies and any attachments, to execute tool calls. This processing happens in isolated, ephemeral environments that are destroyed after use. Vinkius never permanently stores your email content; access is controlled by your API key.

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