How to Use the Churnkey MCP in LlamaIndex

Q: How do I connect LlamaIndex to a Churnkey server?

Use the llama-index-tools-mcp library. You instantiate the BasicMCPClient with the MCP server URL from Vinkius, wrap it in an McpToolSpec, and then call totoollistasync() to get tools your LlamaIndex agent can use.

Q: Can I build a RAG pipeline on Churnkey cancellation data with LlamaIndex?

Absolutely. That's the main idea. You use tools like listretentionsessions to fetch the data and then use LlamaIndex's ingestion pipeline to chunk, embed, and index it into your chosen vector store.

Q: How do I handle GDPR requests?

You can use the getcustomergdprdata and deletecustomergdprdata tools directly. For RAG, remember that if you delete data in Churnkey, you also need to remove it from your LlamaIndex vector store to stay compliant.

Turn your Churnkey retention data into a queryable knowledge base using LlamaIndex and RAG.

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 LlamaIndex

Create your Vinkius account to connect Churnkey to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Cancellation Sessions

Stop guessing why customers leave. Use LlamaIndex to build a real knowledge base from your Churnkey data. The `McpToolSpec` lets you pull data with `list_retention_sessions` and `get_retention_session_details` and feed it directly into a vector index. Now your agent can answer questions in plain English, like "what were the top 3 cancellation reasons last month?". The answers are grounded in your actual session data, not just the model's general knowledge.

Build a Customer-360 RAG App

This isn't just for aggregate data. You can create a detailed, queryable profile for every customer. Your LlamaIndex pipeline can periodically run `get_customer_gdpr_data` and `list_customer_retention_history` for active customers and update their records in your index. When your support team gets a ticket, they can ask the RAG app, "Show me the last three cancellation attempts for customer X and what they said." The agent finds the relevant documents in your index and gives a summarized, accurate answer instantly. This MCP Server provides the live data feed.

Make Smarter Decisions with LlamaIndex

Your agent can now use its knowledge base to make better choices. Before deciding to act, it can query the index for similar, past situations. For instance, it could check "what was the outcome when we updated billing contacts for customers in this segment?". Based on the retrieved data, the agent can then make an informed call on whether to use `update_billing_contacts` or try a different approach. It turns reactive tool use into a data-driven strategy, all powered by a single MCP server.

Setup guide

Set up Churnkey MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Churnkey MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Churnkey tools.",
)
response = await agent.run("List recent Churnkey data")

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 LlamaIndex

Use the `llama-index-tools-mcp` library. You instantiate the `BasicMCPClient` with the MCP server URL from Vinkius, wrap it in an `McpToolSpec`, and then call `to_tool_list_async()` to get tools your LlamaIndex agent can use.

Absolutely. That's the main idea. You use tools like `list_retention_sessions` to fetch the data and then use LlamaIndex's ingestion pipeline to chunk, embed, and index it into your chosen vector store.

Speed and context. Instead of hitting the Churnkey API for every question, your agent queries a local, optimized index. This gives you faster answers and lets you ask complex, semantic questions about trends over time.

You can use the `get_customer_gdpr_data` and `delete_customer_gdpr_data` tools directly. For RAG, remember that if you delete data in Churnkey, you also need to remove it from your LlamaIndex vector store to stay compliant.

The Vinkius MCP Server provides a secure pipe to fetch Churnkey customer data, including PII and session details. Once fetched, the data's security is your responsibility within your LlamaIndex application and vector database. Vinkius ensures the transport is secure and ephemeral, but not what you do with the data afterward.

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