How to Use the ManyChat MCP in LangChain

Q: How do I use LangChain to send a ManyChat flow automatically?

You give the sendflow tool to your LangChain agent. When the agent's goal is to send a flow to a specific user, it will call that tool with the subscriber's ID and the flow ID.

Q: What's the best way to manage ManyChat tags with LangChain agents?

Use the addtag and removetag tools as part of a larger chain. For example, an agent could check purchase history from another API, then decide to call addtag to segment the user in ManyChat.

Build multi-step ManyChat automations that reason and act, all within your LangChain agent.

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 LangChain

Create your Vinkius account to connect ManyChat to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Subscriber Lookups and Tagging

Find a subscriber using their name with `find_subscriber_by_name`. The next step in your chain uses that subscriber's ID to check their current status with `get_subscriber_info`. Based on that output, your agent decides what to do next. If they're a new customer, the chain's final link calls `add_tag` to label them 'onboarding'. Each step is visible in LangSmith, so you see exactly what the agent decided and why.

Trigger Flows Based on Real-Time Logic

Your LangChain agent can do more than just follow a script. It can check a user's state with `get_subscriber_tags`, see they have a 'trial_expired' tag, and decide to trigger a specific win-back campaign using `send_flow`. This isn't a simple 'if-this-then-that' rule. The agent reasons over the data. You can build complex logic, like checking for multiple tags or custom field values, before it acts. This MCP Server makes your agent a true marketing operator.

Build Self-Correcting ManyChat Workflows

Your ManyChat setup can get messy. Use an agent to maintain it. Have it periodically run `list_custom_fields` and compare the output to a master list you've defined. If a field is missing or named incorrectly, the agent can log the issue or even attempt to fix subscriber data with `set_custom_field`. It's an automated data steward for your messenger marketing.

Setup guide

Set up ManyChat MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes ManyChat tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "manychat-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent ManyChat transactions"
    })
    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 LangChain

You give the `send_flow` tool to your LangChain agent. When the agent's goal is to send a flow to a specific user, it will call that tool with the subscriber's ID and the flow ID.

Yes, this is a perfect use for LangChain. You can create a chain that uses `find_subscriber_by_name`, then `add_tag`, and finally `send_flow` to kick off a welcome sequence.

Use the `add_tag` and `remove_tag` tools as part of a larger chain. For example, an agent could check purchase history from another API, then decide to call `add_tag` to segment the user in ManyChat.

Most integrations are just triggers. With this MCP Server, your LangChain agent can reason, execute multi-step logic, and use the output of one tool to inform the input of the next. It's dynamic, not static.

Your agent calls the MCP Server, which runs in a sandboxed V8 isolate on Vinkius. It only processes the specific data needed for the tool call—like subscriber IDs, names, and tags. The data is ephemeral and gone after the call completes.

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