How to Use the Churnkey MCP in CrewAI

Q: How would I build a human approval step for a GDPR deletion using Churnkey and CrewAI?

You'd design a crew where one agent performs the getcustomergdprdata lookup and presents the information for review. Then, you configure the crew to wait for a human callback or external trigger before allowing the agent with the deletecustomergdprdata tool to run.

Deploy an autonomous CrewAI team to monitor churn, manage GDPR, and recover customers with these Churnkey tools.

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 CrewAI

Create your Vinkius account to connect Churnkey to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Churn Monitoring Crew

Assign a "Churn Analyst" agent in your CrewAI setup. Its job is to monitor the health of your customer base by periodically calling `get_session_aggregates` and `list_retention_sessions`. This agent's goal is to spot negative trends or unusual activity. When the Analyst agent finds a pattern—like a spike in cancellations from a certain plan—it tasks a "Retention Researcher" agent. This second agent uses `get_retention_session_details` and `list_customer_retention_history` to dig into the specific sessions, gathering context to pass on for action.

Automate Billing Recovery with a Crew

Create a "Recovery Scout" agent whose only tool is `list_retention_sessions`. Its mission is to find cancellation sessions caused by failed payments and pass the customer IDs to the next agent in the crew. A second "Billing Operations" agent receives the list of customer IDs. It's equipped with `update_billing_contacts` and `bulk_update_billing_contacts`. This agent's job is to execute the updates, coordinating with other systems if needed, to fix the billing issue before the customer churns for good.

A Dedicated GDPR Compliance MCP Server

Set up a "Compliance Auditor" agent to handle data access requests. When a user asks for their data, this agent uses `get_customer_gdpr_data` to collect everything Churnkey has on file. The agent then formats this data and hands it off. It's a single-purpose, reliable tool handler. For deletion requests, a "Data Steward" agent takes over. This agent is the only one in your organization given access to the `delete_customer_gdpr_data` tool. CrewAI lets you create this separation of duties, ensuring a powerful tool is only used in the correct context by a specialized agent.

Setup guide

Set up Churnkey MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Churnkey tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Churnkey Analyst",
    goal="Access and analyze Churnkey data via MCP.",
    backstory="Expert analyst with direct Churnkey access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Churnkey transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Churnkey Analyst",
        goal="Access and analyze Churnkey data via MCP.",
        backstory="Expert analyst with direct Churnkey access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Churnkey transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

This is central to how CrewAI works. The first agent's task returns the output from a Churnkey tool, like a list of customer IDs. You define the next task in the sequence to accept this output as its input, allowing the second agent to act on the data.

Yes. When you define an agent in CrewAI, you assign it a specific list of tools. You can create one agent that only has access to `list_retention_sessions` and another that only has `delete_customer_gdpr_data`, enforcing role-based permissions.

The simplest method is to pass your Vinkius MCP URL directly into the `mcps` list when creating your Agent. For more control, like filtering tools, you can use the `MCPServerHTTP` class from `crewai.mcp` to define the connection more explicitly.

You'd design a crew where one agent performs the `get_customer_gdpr_data` lookup and presents the information for review. Then, you configure the crew to wait for a human callback or external trigger before allowing the agent with the `delete_customer_gdpr_data` tool to run.

The server processes customer record identifiers, billing contact information like emails, and detailed cancellation session data. Each tool call from your CrewAI agent is authenticated via your Vinkius token and executed in a secure, single-use Vinkius sandbox environment.

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