Can my AI automatically detect a declining card and cancel the recurring subscription?

Yes. Ask the agent to pull the most recent invoices and find the specific declined charges. Once identified, command the agent to cancel the associated subscription ID completely, putting an end to the service. All done natively through chat.

How does the Hosted Checkout generation work?

When asked, the AI fetches your catalog items, finds the needed Plan ID, and hits the `generate_hosted_checkout` endpoint. It replies instantly with an ephemeral, safe URL you can copy-paste to your customer, capturing their payment securely before destroying the link lifespan.

Can I halt billing charges for a specific timeframe?

Certainly. The `pause_subscription` command instructs Chargebee to freeze active charges and renewals on the provided subscription ID until you deliberately tell the AI to resume it later. Brilliant for seasonal B2B accounts.

Chargebee MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Chargebee
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

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

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

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

        result = await Runner.run(
            agent, "List all available tools from Chargebee"
        )
        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 Chargebee MCP Server

Connect your Chargebee environment to any AI agent and take absolute control of your SaaS revenue operations by simply chatting. Bypass massive spreadsheets and complex financial dashboards.

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

What you can do

Customers — List existing accounts, retrieve specific financial details (outstanding balances), or create brand new B2B accounts instantly
Subscriptions — Inspect active, trailing, or cancelled plans. Pause renewals, trace MRR, or irreversibly cancel subscriptions mid-term
Invoices — Retrieve active billing logs and check if a payment gateway approved or declined a specific charge
Checkout & Catalog — Enumerate product lines and generate ephemeral, secure Hosted Checkout URLs to capture customer cards on the fly

The Chargebee 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.

How to Connect Chargebee to OpenAI Agents SDK via MCP

Follow these steps to integrate the Chargebee MCP Server with OpenAI Agents SDK.

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 Chargebee

Why Use OpenAI Agents SDK with the Chargebee MCP Server

OpenAI Agents SDK provides unique advantages when paired with Chargebee 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

Chargebee + OpenAI Agents SDK Use Cases

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

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

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

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

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

Chargebee MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Chargebee to OpenAI Agents SDK via MCP:

cancel_subscription

Irreversibly vaporize explicit validations extracting rich Churn flags

create_customer

Provision a highly-available JSON Payload generating hard Customer records

generate_hosted_checkout

Dispatch an automated validation check routing explicit Payment UI

get_customer_details

Perform structural extraction of properties driving active Account logic

get_subscription_details

Inspect deep internal arrays mitigating specific Plan Math

list_catalog_items

Retrieve the exact structural matching verifying Product mapping

list_customers

Identify bounded CRM records inside the Headless Chargebee Platform

list_invoices

Enumerate explicitly attached structured rules exporting active Billing

list_subscriptions

Retrieve explicit Cloud logging tracing explicit Recurring limits

pause_subscription

Identify precise active arrays spanning native Pause tracking

Example Prompts for Chargebee in OpenAI Agents SDK

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

"Create a new customer profile for John Doe at john@acme.com."

"Cancel subscription sub_4001, but wait until the end of the term."

"Review my invoices and point out any recent declines."

Troubleshooting Chargebee MCP Server with OpenAI Agents SDK

Common issues when connecting Chargebee 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.

Chargebee + OpenAI Agents SDK FAQ

Common questions about integrating Chargebee 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.