How to Use the Mailtrap MCP in Google ADK

Q: Can my Google ADK agent read multiple Mailtrap inboxes at once?

The agent calls listsandboxes to find all available test environments. It can then loop through each ID and pull down messages using its long-context memory to analyze them in bulk.

Q: Is it possible to delete specific Mailtrap messages with Google ADK?

You can instruct the agent to run deletesandboxmessage for individual items. This is useful when your Gemini model spots a specific anomaly and wants to remove it without wiping the rest of the test data.

Q: How do I map Mailtrap projects in Google ADK?

Expose the listaccessibleaccounts and listmailtrapprojects tools to your agent. It will query the API and can store that hierarchical data straight into BigQuery for your reporting dashboards.

Give Google ADK agents the ability to QA email templates, manage Mailtrap sandboxes, and trigger production sends from your cloud data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mailtrap MCP to Google ADK

Create your Vinkius account to connect Mailtrap 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 Mailtrap with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Google ADK Sandbox Management

Gemini models use `list_sandbox_messages` to ingest thousands of test emails at once thanks to their massive context windows. Your Google ADK agent pulls message histories from BigQuery, cross-references them with recent test sends, and identifies missing transactional emails. It handles the heavy lifting of parsing headers and metadata. When the analysis finishes, the agent fires `clear_sandbox_inbox` to reset the environment. This keeps your Mailtrap account under its storage limits while maintaining a clean state for the next batch of automated tests.

Trigger Production Campaigns

Enterprise workflows often require sending alerts based on database triggers, and your agent does exactly that with `send_production_email`. It queries Vertex AI for the right copy, validates the target audience, and pushes the message out. The agent checks `list_verified_domains` first to ensure the sender address is authorized. You can restrict which tools the agent sees by using the tool_names filter in your setup. If you only want it sending emails and checking `get_domain_status`, you block access to the sandbox deletion tools entirely.

Deep HTML Inspection MCP Server

Fetching raw template code with `get_message_html` lets your agent spot rendering flaws before they hit production. It reads the inline CSS and compares it against known email client quirks stored in your Google Cloud databases. Linking this MCP Server directly to your Gemini workflow means the agent can rewrite broken HTML on the fly. It pushes the fixed version back through `send_test_email` and verifies the new output using `get_message_details`.

Setup guide

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

Install the google-adk package and initialize an McpToolset with your Vinkius HTTP URL. Pass that toolset directly into the tools array of your LlmAgent configuration.

The agent calls list_sandboxes to find all available test environments. It can then loop through each ID and pull down messages using its long-context memory to analyze them in bulk.

You can instruct the agent to run delete_sandbox_message for individual items. This is useful when your Gemini model spots a specific anomaly and wants to remove it without wiping the rest of the test data.

Expose the list_accessible_accounts and list_mailtrap_projects tools to your agent. It will query the API and can store that hierarchical data straight into BigQuery for your reporting dashboards.

The integration handles sensitive SMTP credentials, raw HTML templates, and test recipient lists. Vinkius routes these requests through a zero-trust, ephemeral execution environment that destroys all memory states the second the API responds.

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