How to Use the MessageFlow MCP in Google ADK

Q: How do I configure MessageFlow with the Google ADK?

Install google-adk and wrap your Vinkius HTTP endpoint in the McpToolset class. Pass this MCP Server toolset directly to your LlmAgent instance. The Gemini model will immediately recognize all ten communication tools.

Q: Can I limit which MessageFlow tools my Google ADK agent can access?

Yes, you can pass a filtered list of tool names to the McpToolset constructor. This prevents the agent from calling administrative tools like getaccountbalance while keeping dispatch tools active.

Q: Does MessageFlow support the long-context windows in Google ADK?

Yes, the agent can ingest large lists of messages from listmessages and process them in a single reasoning step. This MCP capability is highly efficient for generating daily delivery summaries.

Q: Can the agent verify account funds before sending messages?

Yes, the agent calls getaccountbalance to verify remaining credits. It can run this check before executing any high-volume dispatch to avoid mid-campaign interruptions.

Connect Gemini agents using the Google ADK to MessageFlow to dispatch multi-channel alerts directly from your Google 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 MessageFlow MCP to Google ADK

Create your Vinkius account to connect MessageFlow 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 MessageFlow with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger bulk messaging from BigQuery datasets

The `send_sms` tool transmits text messages directly to customers based on database triggers. Your Gemini agent queries your BigQuery tables, extracts recipient lists, and executes the dispatch in a single loop. It manages high-volume queues without requiring manual middleware. You can restrict the toolset to only expose specific endpoints if you want to limit agent actions. The agent handles the structural formatting and passes the payload directly to the gateway.

Deploy localized templates using Gemini's long context

The `list_templates` tool retrieves your entire library of communication layouts for the agent to analyze. Because Gemini handles massive token contexts, the agent can compare dozens of templates from `get_template` to select the most relevant message style for a user's history. This setup avoids hardcoding template IDs in your application logic. The agent evaluates the user's intent, picks the matching template, and runs `send_whatsapp` or `send_email` on the spot.

Track delivery metrics using this MCP Server

The `get_delivery_status` tool queries the real-time state of any message dispatch. Your agent uses this MCP tool to monitor delivery pipelines and write status reports back to your Google Cloud database. It tracks whether messages are delivered, pending, or failed. If a failure occurs, the agent calls `list_messages` to diagnose the issue. It checks the error logs, verifies the channel configuration via `list_channels`, and alerts your operations team if a gateway goes offline.

Setup guide

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

Install `google-adk` and wrap your Vinkius HTTP endpoint in the `McpToolset` class. Pass this MCP Server toolset directly to your `LlmAgent` instance. The Gemini model will immediately recognize all ten communication tools.

Yes, you can pass a filtered list of tool names to the `McpToolset` constructor. This prevents the agent from calling administrative tools like `get_account_balance` while keeping dispatch tools active.

Yes, the agent can ingest large lists of messages from `list_messages` and process them in a single reasoning step. This MCP capability is highly efficient for generating daily delivery summaries.

Yes, the agent calls `get_account_balance` to verify remaining credits. It can run this check before executing any high-volume dispatch to avoid mid-campaign interruptions.

All recipient contact details and message strings are processed in memory within secure, isolated V8 containers. No contact data is stored on disk, maintaining strict security for this MCP Server.

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