How to Use the Churnkey MCP in AutoGen

Q: How do AutoGen agents access the Churnkey tools?

You use the mcpservertools function from the autogen-extmcp package, passing it your Vinkius server URL. This returns a list of tools that you can provide directly to your AssistantAgent or UserProxyAgent.

Q: What does a strategy debate between AutoGen agents using Churnkey data look like?

It's a chat log. You'll see one agent present data from getsessionaggregates, another propose a solution using bulkupdatebillingcontacts, and a third agent challenge the proposal, asking for more specific data from getretentionsessiondetails.

Let a team of AutoGen agents debate, plan, and execute Churnkey retention strategies for you.

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 AutoGen

Create your Vinkius account to connect Churnkey to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create an AI Compliance Committee

Use AutoGen's multi-agent conversations to build a robust GDPR workflow. You can set up one agent as a `ComplianceOfficer` that's allowed to use `get_customer_gdpr_data`. It presents its findings to a second `DeletionAuditor` agent. Only after the `DeletionAuditor` agent gives its approval in the chat can the `ComplianceOfficer` proceed to use the `delete_customer_gdpr_data` tool. This creates a system of checks and balances, with all actions dispatched through the secure MCP server.

Debate Churn-Fighting Strategies

Turn churn analysis into a collaborative process. An `Analyst` agent can use `get_session_aggregates` to spot a problem and report it to the group. A `Strategist` agent might immediately suggest using `bulk_update_billing_contacts` to roll out a fix. But a `Finance` agent can push back, asking the `Analyst` to first use `get_retention_session_details` on a few specific examples to confirm the root cause. This debate ensures you don't waste effort on the wrong solution. It's a team meeting, but with agents.

Multi-Agent Customer Interventions

Handle at-risk customers with a dedicated team of agents. When a high-value customer starts a cancellation flow, a `Scout` agent can use `list_customer_retention_history` to pull their past interactions. A second `Valuation` agent can check their LTV from a separate database. Together, they can discuss the situation and decide if an intervention is warranted. If they agree, a third `Executor` agent is tasked with calling `update_billing_contacts` to add a white-glove recovery specialist's contact info. This MCP Server gives them the tools to act on their decisions.

Setup guide

Set up Churnkey MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Churnkey tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Churnkey_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Churnkey data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Churnkey_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Churnkey data")
    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 AutoGen

You use the `mcp_server_tools` function from the `autogen-ext[mcp]` package, passing it your Vinkius server URL. This returns a list of tools that you can provide directly to your `AssistantAgent` or `UserProxyAgent`.

Yes, that's a perfect use case for AutoGen's multi-agent conversations. You can create separate agents with different permissions and require them to agree on a course of action before one of them is allowed to call `delete_customer_gdpr_data`.

It's a chat log. You'll see one agent present data from `get_session_aggregates`, another propose a solution using `bulk_update_billing_contacts`, and a third agent challenge the proposal, asking for more specific data from `get_retention_session_details`.

AutoGen handles this well. When you define your agents, you can provide each one with a specific subset of the Churnkey tools returned by the MCP server. This lets you create specialist agents, like one that can only read data and another that can only write.

Data like customer PII and session history is fetched via the secure Vinkius MCP Server and then passed as text within the agent conversation. Security depends on your AutoGen setup; the data exists in-memory in the Python process where the agents are running. Vinkius secures the pipe, you secure the conversation 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