How to Use the Messaggio MCP in Google ADK

Q: How do I register the Messaggio MCP Server inside my Google ADK setup?

Run pip install google-adk to get the library. Then, construct an McpToolset pointing to your HTTP server URL and pass it into the tools parameter of your LlmAgent.

Q: Can Gemini analyze campaign performance using Messaggio and Google ADK?

Yes, your agent can call listmessages to pull historical dispatch logs into its context window. Gemini then parses the delivery outcomes to generate performance summaries or suggest template tweaks.

Q: How does Google ADK handle bulk dispatches through Messaggio?

The agent invokes sendbulk with a payload structured from your enterprise database. Gemini manages the rate limits and ensures the batch payload adheres to the API schema before initiating the call.

Q: Can I limit which tools the Gemini model can execute?

Yes, you can pass a specific list of tool names to your McpToolset configuration. This prevents the model from calling administrative tools like listprojects if it only needs to send messages via the MCP interface.

Feed BigQuery data directly into WhatsApp and SMS campaigns using the Google ADK and Gemini models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Messaggio MCP to Google ADK

Create your Vinkius account to connect Messaggio 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 Messaggio with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Google ADK Dispatches from BigQuery Data

The `send_simple_sms` tool allows your Google ADK agent to read customer lists from BigQuery and immediately dispatch text notifications through the MCP Server. By combining Gemini's long-context reasoning with direct database access, your agent personalizes thousands of individual messages without manual scripting. The agent uses `list_project_senders` to map regional phone numbers to the correct sender profile based on the recipient's country code. This ensures your cloud-hosted agent always complies with local telecom regulations.

Monitor Delivery Pipelines within Google Cloud

The `get_message_status` tool tracks whether your WhatsApp or Viber messages actually landed on the recipient's device using this MCP pipeline. Your Google ADK agent queries this endpoint to update custom dashboards or trigger automated email follow-ups. If delivery rates drop, the agent runs `check_messaggio_status` to verify connection health. This automated monitoring loop keeps your enterprise communication channels transparent and accountable.

Manage Templates Dynamically inside Gemini Context

The `list_templates` tool pulls your approved message structures directly into Gemini's active context window. Because the Google ADK handles long-context inputs, your agent can evaluate hundreds of templates simultaneously to select the best match. Once selected, the agent calls `get_template` to inspect the exact parameters needed for the WhatsApp or Viber payload. This programmatic selection prevents formatting errors and speeds up campaign preparation.

Setup guide

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

Run `pip install google-adk` to get the library. Then, construct an `McpToolset` pointing to your HTTP server URL and pass it into the `tools` parameter of your `LlmAgent`.

Yes, your agent can call `list_messages` to pull historical dispatch logs into its context window. Gemini then parses the delivery outcomes to generate performance summaries or suggest template tweaks.

The agent invokes `send_bulk` with a payload structured from your enterprise database. Gemini manages the rate limits and ensures the batch payload adheres to the API schema before initiating the call.

Yes, you can pass a specific list of tool names to your `McpToolset` configuration. This prevents the model from calling administrative tools like `list_projects` if it only needs to send messages via the MCP interface.

Recipient phone numbers and SMS text payloads pass through isolated, ephemeral memory blocks. The Vinkius gateway does not log your API keys or message contents, ensuring your customer data remains compliant with enterprise security standards.

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