How to Use the Customer.io MCP in LangChain

Q: How do I connect LangChain to the Customer.io API?

Install langchain-mcp-adapters and initialize a MultiServerMCPClient. Pass your Vinkius endpoint URL to the client, then call gettools() to expose the marketing tools to your ReAct agent.

Q: What context does LangChain maintain between Customer.io queries?

The client is stateless by default. You need to use client.session() if you want the agent to remember a specific campaign ID between fetching the broadcast list and querying its performance.

Build multi-step marketing workflows with LangChain. Chain Customer.io engagement data directly into your reasoning pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customer.io MCP to LangChain

Create your Vinkius account to connect Customer.io 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 Customer.io with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Customer.io MCP Server tools

LangChain agents excel at sequential logic. You feed an email address into `search_customers_by_email`, grab the resulting identifier, and immediately pass it to `get_customer_details`. The agent handles the intermediate routing automatically. Tracing these marketing workflows is straightforward. LangSmith captures every token spent querying `get_campaign_performance` or `get_engagement_summary`, showing exactly how your agent decided which campaign needed attention.

Update profiles dynamically

ReAct agents can monitor external databases and sync states directly to your workspace. When a user completes a purchase in your app, the agent fires `identify_customer` to update their custom attributes and device tokens. You build the reasoning loop, and the agent executes the mutations. It pulls the current state using `list_customers`, compares it against your vector store, and applies the necessary attribute updates without manual intervention.

Analyze broadcast segments

Combine audience data with external APIs in a single pipeline. Your agent pulls dynamic audience lists via `list_customer_segments` and checks membership counts before triggering any external alerts. Fetching message metadata works the same way. The agent runs `list_broadcast_messages` or `list_automated_campaigns`, extracts the scheduling data, and formats it for your internal reporting tools.

Setup guide

Set up Customer.io 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 Customer.io 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({
    "customerio-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 Customer.io 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 Customer.io. 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 Customer.io 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 Customer.io MCP in LangChain

Install `langchain-mcp-adapters` and initialize a `MultiServerMCPClient`. Pass your Vinkius endpoint URL to the client, then call `get_tools()` to expose the marketing tools to your ReAct agent.

Yes, the agent can mutate workspace identity data. It uses the `identify_customer` tool to modify custom attributes or device tokens based on pipeline logic.

Yes. Every call to fetch engagement metrics or segment data appears in your LangSmith dashboard. You see exact latency and token usage for each tool invocation.

The client is stateless by default. You need to use `client.session()` if you want the agent to remember a specific campaign ID between fetching the broadcast list and querying its performance.

Vinkius isolates your environment in a V8 sandbox. When your agent pulls email addresses and device tokens, that information stays within the ephemeral session and never touches our permanent storage.

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