How to Use the Customerly MCP in LangChain

Q: How do I manage user segments in Customerly with a LangChain agent?

Your agent can use the addtag and removetag tools. You can create chains that automatically segment users based on their attributes or conversation history, letting you build dynamic cohorts.

Q: Can a LangChain agent create a new user in Customerly and then add them to a campaign?

Yes, that's a perfect use case. The agent would call createupdateuser first, then use the returned user ID to call addtag with your campaign tag. It's a two-step chain the agent executes from one prompt.

Q: Can I delete users from Customerly with an agent?

Yes, the deleteuser tool is available. Be careful with this one; it's a permanent action. We recommend building guards into your agent's logic to prevent accidental deletions.

Build Customerly automation chains in LangChain. Your agent can now create users, tag them, and check conversation history in one sequence.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customerly MCP to LangChain

Create your Vinkius account to connect Customerly 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 Customerly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate User Onboarding Flows

Your LangChain agent can now manage the entire user lifecycle in Customerly. Use a single prompt to `create_update_user`, then immediately `add_tag` to segment them into an onboarding campaign. The agent figures out the steps; you just define the goal. This isn't just a one-off script. You can build ReAct agents that decide which tags to add based on user properties or past conversations. It's a dynamic system that responds to data, not just a fixed set of commands.

Chain Customer Data for Analysis

Connect Customerly data to other tools in your chain. Your agent can `list_users`, pipe that list into a database tool, and then use `get_conversation` to pull specific interaction details for anyone who hasn't logged in recently. LangSmith gives you a full trace of these operations. You see exactly how your agent fetched the user list, why it chose to get a specific conversation, and how long each step took. Debugging complex customer data chains is no longer a black box.

Dynamic Lead Management with LangChain

Go beyond static lead forms. An agent can listen to an event from another service, use `create_update_lead` in Customerly, and then decide the next action based on the lead's profile data. It's event-driven marketing automation. This Customerly MCP Server gives your agents the primitives to act. They can `remove_tag` when a trial ends or `add_tag` when a user visits the pricing page. You're building an autonomous system that manages your marketing funnel.

Setup guide

Set up Customerly 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 Customerly 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({
    "customerly-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 Customerly 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 Customerly. 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 Customerly 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 Customerly MCP in LangChain

Your agent can use the `add_tag` and `remove_tag` tools. You can create chains that automatically segment users based on their attributes or conversation history, letting you build dynamic cohorts.

Yes, that's a perfect use case. The agent would call `create_update_user` first, then use the returned user ID to call `add_tag` with your campaign tag. It's a two-step chain the agent executes from one prompt.

Create a chain that reads from your database, then uses the `create_update_user` tool. Your agent can handle the logic for creating new users or updating existing ones based on their email address.

Yes, the `delete_user` tool is available. Be careful with this one; it's a permanent action. We recommend building guards into your agent's logic to prevent accidental deletions.

Your Vinkius endpoint token authenticates all requests. The connection between your LangChain agent and the MCP Server is encrypted. No raw user data, like emails or conversation content, is ever stored by Vinkius; it's passed directly to Customerly's API.

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