How to Use the Churnkey MCP in LangChain

Q: How do I build a Churnkey agent with LangChain?

It's straightforward. You'll use the MultiServerMCPClient to connect to this MCP server's endpoint. Then, call client.gettools() and pass the resulting list of Churnkey tools directly to your LangChain agent constructor.

Q: Can a LangChain agent handle Churnkey GDPR requests automatically?

Yes, that's a core use case. Your agent can chain the getcustomergdprdata and deletecustomergdprdata tools to create a complete, auditable GDPR workflow. LangSmith tracing gives you a full record of the process.

Q: What's the best way to analyze Churnkey session data in LangChain?

Use a chain. Start with getsessionaggregates for a high-level view. From there, your agent can decide to drill down into specific cohorts or individual customers using listretentionsessions and getretentionsessiondetails.

Build autonomous retention chains that analyze churn and update customer billing contacts, 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 Churnkey MCP to LangChain

Create your Vinkius account to connect Churnkey 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 Churnkey with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate GDPR Compliance

This MCP server gives your agent tools to handle GDPR requests from start to finish. A single chain can get a customer's data with `get_customer_gdpr_data`, log it for auditing, and then permanently remove it using `delete_customer_gdpr_data`. No manual steps needed. Because it's a LangChain agent, you get full visibility in LangSmith. You can trace the entire flow, see the exact data passed to each tool, and confirm the deletion was successful. It's a fully observable compliance machine.

Build Proactive Retention Workflows with this MCP Server

Don't just react to cancellations. Build agents that look for trouble. Your chain can start by calling `get_session_aggregates` to find patterns in recent cancellation sessions. If it spots a trend, it can dig deeper on specific accounts with `list_customer_retention_history`. Once your agent identifies at-risk customers, it can act immediately. The chain can finish by calling `update_billing_contacts` or `bulk_update_billing_contacts` to add a specific recovery contact, automatically starting a retention campaign.

Chain Churnkey with Other APIs

The real power here is connecting Churnkey to your other systems. Your agent isn't limited to just these tools. You can build a chain that first pulls a list of high-value customers from your CRM's API. Then, for each of those customers, the agent can check their status in Churnkey using `list_customer_retention_history`. If they've had recent cancellation attempts, the agent can trigger a Slack alert and update their billing info with `update_billing_contacts`, all in one go.

Setup guide

Set up Churnkey 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 Churnkey 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({
    "churnkey-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 Churnkey 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 Churnkey. 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 Churnkey 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 Churnkey MCP in LangChain

It's straightforward. You'll use the `MultiServerMCPClient` to connect to this MCP server's endpoint. Then, call `client.get_tools()` and pass the resulting list of Churnkey tools directly to your LangChain agent constructor.

Yes, that's a core use case. Your agent can chain the `get_customer_gdpr_data` and `delete_customer_gdpr_data` tools to create a complete, auditable GDPR workflow. LangSmith tracing gives you a full record of the process.

Use a chain. Start with `get_session_aggregates` for a high-level view. From there, your agent can decide to drill down into specific cohorts or individual customers using `list_retention_sessions` and `get_retention_session_details`.

Vinkius handles it. You get a single endpoint token for your LangChain environment. The `langchain-mcp-adapters` library uses that token to authenticate every tool call automatically.

Yes. The server only exposes specific Churnkey customer data like billing contacts and session history. Vinkius runs each MCP Server in a V8 Isolate sandbox, so every request is ephemeral and isolated. Your token authenticates the request, but the data itself doesn't persist on the server after the chain runs.

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