How to Use the MailSlurp MCP in Google ADK

Q: How do I configure MailSlurp with Google ADK?

Install google-adk via pip. Initialize a McpToolset using StreamableHttpServerParameters with your Vinkius endpoint URL. Pass this toolset to your LlmAgent to expose the email functions.

Q: Can I restrict which MailSlurp tools Google ADK can access?

Yes, you can pass a toolnames filter when setting up the toolset. This lets you expose listinboxemails while blocking destructive actions like deleting the inbox.

Q: Can I query all my MailSlurp test addresses through Google ADK?

Calling listallinboxes returns an array of your active endpoints. Your agent can process this list and cross-reference it with test data stored in Vertex AI or BigQuery.

Connect MailSlurp to Google ADK to run massive email testing pipelines on Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MailSlurp MCP to Google ADK

Create your Vinkius account to connect MailSlurp 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 MailSlurp with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Provision inboxes with Google ADK

The `create_random_inbox` tool provisions temporary email addresses straight from your Gemini agent. You generate fresh endpoints for every test run, ensuring absolute isolation between parallel execution threads. The agent tracks the generated IDs and credentials in its massive context window. Cleaning up requires a quick call to `delete_specific_inbox`. Your pipeline drops the temporary address and all associated messages the moment the verification step finishes. This strict lifecycle management keeps your account limits clear for the next batch.

Validate complex email sequences

The `wait_for_email_count` tool blocks pipeline execution until a specific number of messages hit the target address. Gemini can trigger a complex onboarding flow in your app, then watch the inbox to confirm all three welcome emails arrive. If you only need the most recent message, `wait_for_latest_email` long-polls the endpoint and returns the payload instantly. Your agent parses the text, extracts the OTP, and pushes it into your BigQuery logs for audit purposes.

Send and inspect messages via MCP Server

The `get_email_details` tool exposes the raw HTML and metadata of any received message. Gemini reads the entire payload to spot broken links, malformed CSS, or missing personalization tags. Your agent can also talk back to your application using `send_email_from_inbox`. It fires off a reply with specific content, letting you test how your backend handles inbound customer support tickets or automated bounces.

Setup guide

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

Install `google-adk` via pip. Initialize a `McpToolset` using `StreamableHttpServerParameters` with your Vinkius endpoint URL. Pass this toolset to your `LlmAgent` to expose the email functions.

Yes, you can pass a `tool_names` filter when setting up the toolset. This lets you expose `list_inbox_emails` while blocking destructive actions like deleting the inbox.

The agent executes the wait functions and pauses its reasoning loop. Once the email arrives, the MCP Server returns the data to Gemini, which then resumes the workflow.

Calling `list_all_inboxes` returns an array of your active endpoints. Your agent can process this list and cross-reference it with test data stored in Vertex AI or BigQuery.

The tools fetch sensitive test data like password reset links and raw email headers. Vinkius forces all traffic through a zero-trust architecture, meaning your temporary credentials and payloads exist only during the active request.

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