How to Use the ManyChat MCP in Google ADK

Q: How do I use ManyChat tools with Google ADK and Gemini?

You instantiate an McpToolset with the Vinkius server URL and pass it to your LlmAgent. The ADK makes all the ManyChat tools from this MCP Server available to your Gemini agent automatically.

Q: Can I automate ManyChat flows from a Google ADK agent?

Absolutely. The agent uses the sendflow tool. You can build logic where the Gemini model decides which flow is most appropriate for a ManyChat subscriber based on data from BigQuery or other Google Cloud services.

Q: What's the process for updating a ManyChat custom field via Google ADK?

The agent calls the setcustomfield tool with the subscriber's ID and the new value. It's a single function call that handles the update in ManyChat for you.

Connect your Gemini agent to ManyChat with the Google ADK and act on your enterprise data in Google Cloud with this MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ManyChat MCP to Google ADK

Create your Vinkius account to connect ManyChat 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 ManyChat with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync BigQuery Insights to ManyChat

Your Gemini agent can run a query in BigQuery to identify a new customer segment. Then, it uses that data to find those users in ManyChat with `find_subscriber_by_custom_field`. It's a direct line from your data warehouse to your marketing channel. Once the agent finds a match, it uses `set_custom_field` to update their ManyChat profile with the new segment info from BigQuery. This keeps your audiences perfectly synced without any manual CSV uploads.

Run Complex Sequences with a Google ADK Agent

A simple chatbot can't handle a real customer journey. A Gemini agent using Google ADK can. It uses its long-context window to analyze the entire conversation history and your internal notes. Based on that deep understanding, the agent can execute a multi-step plan. It might use `add_tag` to mark interest, wait, then `send_flow` to deliver a targeted offer. This MCP server gives your agent the tools to do it.

Create a Data Loop with Vertex AI

Don't let your ManyChat data sit in a silo. An agent can periodically run `get_subscriber_info` and `get_subscriber_tags` for active users. It then feeds that information back into a Vertex AI model. This creates a powerful feedback loop. Your models get smarter based on real user interactions in Messenger, and your agent's actions in ManyChat get more precise.

Setup guide

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

You instantiate an `McpToolset` with the Vinkius server URL and pass it to your `LlmAgent`. The ADK makes all the ManyChat tools from this MCP Server available to your Gemini agent automatically.

Absolutely. The agent uses the `send_flow` tool. You can build logic where the Gemini model decides which flow is most appropriate for a ManyChat subscriber based on data from BigQuery or other Google Cloud services.

The MCP server acts as a secure bridge. Your Google ADK agent makes a request, Vinkius authenticates it and translates it into a direct ManyChat API call, then returns the result.

The agent calls the `set_custom_field` tool with the subscriber's ID and the new value. It's a single function call that handles the update in ManyChat for you.

The connection only handles subscriber information like names, tags, and custom field data required by the tools. Your data is protected by Google Cloud's robust IAM permissions on your end and Vinkius's zero-trust architecture that isolates every single API call.

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