Can I manually start a retention flow for a customer via AI?

Yes! Use the `start_flow` tool and provide the Flow ID, Customer ID, and Subscription ID. This will initialize the retention experience for that user immediately.

How do I see if a customer successfully stayed after a flow?

Run the `get_flow_session` query with the specific Session ID. It will return the outcome and status of the retention attempt.

Is it possible to update a subscription's status via AI?

Absolutely. Use the `update_subscription` tool by providing the Subscription ID and the new status to synchronize data between your systems and Upzelo.

INSTANT PLUG AND PLAY

Upzelo MCP Server for OpenAI Agents SDKGive OpenAI Agents SDK instant access to 10 tools to Get Customer, Get Flow, Get Flow Session, and more

Name: Upzelo
Availability: InStock
Author: Vinkius

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Upzelo through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Use with Your AI Agent

Ask AI about this App Connector for OpenAI Agents SDK

Open in ChatGPT Open in Claude Open in Perplexity

The Upzelo app connector for OpenAI Agents SDK is a standout in the Sales Automation category — giving your AI agent 10 tools to work with, ready to go from day one.

Vinkius delivers Streamable HTTP and SSE to any MCP client

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Upzelo Assistant",
            instructions=(
                "You help users interact with Upzelo. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Upzelo"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Upzelo MCP Server

Connect your Upzelo churn management account to any AI agent and simplify how you retain customers and manage subscription lifecycles through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Upzelo through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Upzelo, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Customer Management — List and search customer records, and update profile data for better segmentation and targeting.
Retention Flows — List available flows and manually trigger retention sequences for customers at risk of cancelling.
Subscription Tracking — Query all tracked subscriptions and update statuses or trial details programmatically.
Flow Monitoring — Check the real-time status and outcomes of active flow sessions to verify retention success.
External ID Sync — Link your internal system identifiers to Upzelo customer records for seamless integration.

The Upzelo MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 10 Upzelo tools available for OpenAI Agents SDK

When OpenAI Agents SDK connects to Upzelo through Vinkius, your AI agent gets direct access to every tool listed below — spanning churn-reduction, subscription-management, customer-retention, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.

get_customer

Get details for a specific customer

get_flow

Get details for a specific flow

get_flow_session

Check the status of a flow session

get_subscription

Get details for a specific subscription

list_customers

List all customers in Upzelo

list_flows

List all retention flows

list_subscriptions

List all subscriptions

save_customer

Used for segmentation and targeting. Create or update a customer record

start_flow

Initialize a flow for a customer

update_subscription

Update subscription attributes

Connect Upzelo to OpenAI Agents SDK via MCP

Follow these steps to wire Upzelo into OpenAI Agents SDK. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Upzelo

Why Use OpenAI Agents SDK with the Upzelo MCP Server

OpenAI Agents SDK provides unique advantages when paired with Upzelo through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Upzelo + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Upzelo MCP Server delivers measurable value.

Automated workflows: build agents that query Upzelo, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Upzelo, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Upzelo tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Upzelo to resolve tickets, look up records, and update statuses without human intervention

Example Prompts for Upzelo in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Upzelo immediately.

"List all customers currently tracked in Upzelo."

"Trigger the 'Basic Retention' flow (ID: fl_8823) for customer 'cust_1029'."

"Show me the details for subscription 'sub_12903'."

Troubleshooting Upzelo MCP Server with OpenAI Agents SDK

Common issues when connecting Upzelo to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Upzelo + OpenAI Agents SDK FAQ

Common questions about integrating Upzelo MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.

Can I use multiple MCP servers in one agent?

Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.

Does the SDK support streaming responses?

Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.