How to Use the ChurnZero MCP in OpenAI Agents SDK

Q: How do I connect ChurnZero to the OpenAI Agents SDK?

Initialize MCPServerStreamableHttp with your Vinkius endpoint URL. Pass the resulting MCP server object into the mcpservers list when constructing your agent. Set cacheToolsList=True to speed up tool discovery.

Q: Can the OpenAI Agents SDK read ChurnZero playbooks?

Yes, the listsuccessplaybooks tool exposes active playbooks to your agent. Your system reads these predefined steps to guide automated customer interactions.

Connect ChurnZero to the OpenAI Agents SDK for production-grade customer health tracking and automated account interventions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChurnZero MCP to OpenAI Agents SDK

Create your Vinkius account to connect ChurnZero to OpenAI Agents SDK 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 ChurnZero with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Account Health via OpenAI Agents SDK

The `get_account_success_details` tool pulls raw customer health metrics directly into your agent's context window via this MCP integration. Your production system can check specific account statuses before triggering automated emails or creating internal tickets. Handoffs between specialized agents require exact data. When a support agent detects frustration, it passes the thread to a retention agent armed with `list_churnzero_alerts` to see if the customer is already marked at risk.

Map Customer Journeys via MCP Server

Fetching active milestones happens through the `list_customer_journeys` tool. You map out exactly where a client sits in their onboarding or renewal phase without leaving your Python environment. OpenAI's built-in guardrails validate these state changes before execution. If an agent tries to push an account to a new phase, the safety constraints ensure the action matches your defined business logic.

Log Events with Full Tracing

Recording user activity relies on the `track_account_event` tool to push usage data back into your success platform. Your agent logs feature adoption metrics right after resolving a technical query. Every single API call flows through the OpenAI dashboard for complete observability. You see exactly when an agent logged the event and what context prompted the decision.

Setup guide

Set up ChurnZero MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all ChurnZero tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives ChurnZero tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate ChurnZero tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="ChurnZero Agent",
            instructions="You have access to ChurnZero tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 ChurnZero. 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 ChurnZero 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 ChurnZero MCP in OpenAI Agents SDK

Initialize `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass the resulting MCP server object into the `mcp_servers` list when constructing your agent. Set `cacheToolsList=True` to speed up tool discovery.

Yes, the `list_success_playbooks` tool exposes active playbooks to your agent. Your system reads these predefined steps to guide automated customer interactions.

The MCP server currently only supports reading contacts via `list_churnzero_contacts`. Write operations are limited to logging events, keeping your core customer records safe from accidental agent modification.

One agent can pull active alerts and pass that context directly to a retention agent. The handoff preserves the full customer history for the next step.

Customer churn scores and journey milestones run through an ephemeral V8 Isolate Sandbox. The connection drops immediately after the API call completes, leaving zero residual data on the server.

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