How to Use the ManyChat MCP in AutoGen

Q: Can AutoGen agents update ManyChat custom fields after a discussion?

Definitely. One agent can find the user with findsubscriberbycustomfield and another can update them with setcustomfield after a debate. It turns a simple update into a verified, multi-step process.

Let your AutoGen agents debate and agree on the right ManyChat actions to take before they happen.

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 AutoGen

Create your Vinkius account to connect ManyChat to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Have Agents Debate Before Tagging Users

Give the `add_tag` tool to a 'MarketerAgent'. When it wants to add a user to a new promo, it has to ask a 'SupportAgent' for permission first. The SupportAgent uses `get_subscriber_info` to check if the user has an open support ticket. If they do, it tells the MarketerAgent to stand down. This prevents sending marketing messages to frustrated users.

Build a Safety Net for Sending Flows

One agent's entire job is to trigger campaigns with `send_flow`. But it can't act alone. It must propose the action to an 'AuditorAgent'. The AuditorAgent's job is to use `get_subscriber_flows` and `get_subscriber_tags` to check for conflicts. Only after the AuditorAgent gives the 'go' signal does the flow get sent. This MCP Server enables true conversational checks.

Let Agents Collaborate on Customer Profiles

Set up a team of agents to manage your data. A 'DataEntryAgent' can use `find_subscriber_by_name` and then update a user's record with `set_custom_field` when new information comes in from another system. A 'SegmentationAgent' listens for those updates. Once a field is set, it automatically calls `add_tag` to put the subscriber in the right bucket. The agents work together, in conversation, to keep your data clean.

Setup guide

Set up ManyChat MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes ManyChat tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="ManyChat_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent ManyChat data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="ManyChat_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent ManyChat data")
    print(result.messages[-1].content)

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 AutoGen

You assign different tools to different agents. For example, a 'MarketingAgent' gets `send_flow`, while a 'ComplianceAgent' gets `get_subscriber_info`. They must discuss and agree before any action is taken.

Yes. This is a core strength. Create an 'AuditorAgent' that must approve any `send_flow` call proposed by another agent. The auditor can use other tools to verify the action is safe before giving approval.

Definitely. One agent can find the user with `find_subscriber_by_custom_field` and another can update them with `set_custom_field` after a debate. It turns a simple update into a verified, multi-step process.

It's built for multi-agent conversation. You give different tools to different agents so they can debate and check each other's work. This prevents a single rogue agent from making a mistake with your customer data.

The server handles ManyChat subscriber data like names, IDs, and tags. Vinkius isolates every tool call in a zero-trust container that is destroyed after execution. Even with multiple agents, each call is a separate, secure transaction and nothing persists.

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