How to Use the Gmelius MCP in Google ADK

Q: How does Google ADK discover the Gmelius MCP Server?

You initialize the McpToolset with your Vinkius HTTP URL in your Python script. The Google ADK automatically registers all 9 tools, making them available to your Gemini agent for immediate execution.

Q: Can I limit which Gmelius tools my Google ADK agent can use?

Yes. You can pass a filtered list of tool names to the McpToolset constructor. For example, you can restrict your agent to only read templates via listgmeliustemplates while blocking card creation.

Connect Gemini models to your Gmelius workspace using Google ADK to analyze shared inboxes alongside BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gmelius MCP to Google ADK

Create your Vinkius account to connect Gmelius 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 Gmelius with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process Massive Inboxes with Google ADK

The `list_gmelius_conversations` tool feeds complete email threads directly into Google ADK for long-context Gemini reasoning. This integration lets your Gemini agent ingest months of shared inbox history at once, identifying recurring support issues without losing track of older messages. By calling `get_gmelius_conversation`, your Google ADK agent retrieves detailed thread histories to cross-reference with customer records stored in BigQuery. This allows the Gemini model to make decisions based on real-time email data and database records.

Sync Gmelius MCP Server Boards with Vertex AI

The `list_gmelius_boards` tool exposes your shared team boards to Google ADK's enterprise agent framework using the MCP Server. Using Google ADK, you can build Gemini agents that monitor project status and update your Google Cloud infrastructure based on what is happening inside your Gmelius workspace. When an external Google Cloud alert occurs, the agent runs `create_gmelius_card` to notify your support team. This keeps your developers and support agents aligned without requiring manual updates in multiple dashboards.

Manage Shared Templates via Google ADK

The `list_gmelius_templates` tool allows your Gemini-powered Google ADK agent to inspect existing email templates. The Google ADK framework uses these templates to generate draft replies, matching the exact tone and structure your sales team expects. To keep campaigns organized, the agent calls `list_gmelius_sequences` to track active email tracks in Gmelius. Because the ADK integrates with your Google Cloud logging, you can audit every sequence modification the agent performs on your templates.

Setup guide

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

You initialize the `McpToolset` with your Vinkius HTTP URL in your Python script. The Google ADK automatically registers all 9 tools, making them available to your Gemini agent for immediate execution.

Yes. You can pass a filtered list of tool names to the `McpToolset` constructor. For example, you can restrict your agent to only read templates via `list_gmelius_templates` while blocking card creation.

You register both the Gmelius toolset and your BigQuery tools within the same `LlmAgent`. The agent can then read email threads using `list_gmelius_conversations` and write the extracted data directly to your warehouse.

You should implement a conditional check in your execution loop. If the status tool returns a failure, your agent can pause operations and log the event to Google Cloud Logging before retrying.

All email conversations and board cards are fetched through secure, ephemeral V8 sandboxes. Your raw Gmail content is never cached on Vinkius, ensuring complete isolation as data moves between Gmelius and Google Cloud.

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