Vinkius
Recharge logo
Vinkius
Vinkius runs on OpenAI Agents SDK

How to Use the Recharge MCP in OpenAI Agents SDK

Run secure, production-grade Recharge subscription changes using OpenAI Agents SDK with built-in guardrails and tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Recharge MCP on Cursor AI Code Editor MCP Client Recharge MCP on Claude Desktop App MCP Integration Recharge MCP on OpenAI Agents SDK MCP Compatible Recharge MCP on Visual Studio Code MCP Extension Client Recharge MCP on GitHub Copilot AI Agent MCP Integration Recharge MCP on Google Gemini AI MCP Integration Recharge MCP on Lovable AI Development MCP Client Recharge MCP on Mistral AI Agents MCP Compatible Recharge MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Vinkius runs on OpenAI Agents SDK

Connect Recharge MCP to OpenAI Agents SDK

Create your Vinkius account to connect Recharge 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

Key Capabilities

Guardrails for destructive Recharge updates in OpenAI Agents SDK

The `cancel_subscription` tool handles sensitive customer state changes that require strict verification before execution. By using this MCP Server with the OpenAI Agents SDK, you can set up runtime guardrails to intercept cancellation requests, ensuring your agent never drops a subscription without verifying customer intent first. You can configure the SDK to trigger a human-in-the-loop confirmation before the agent calls `update_subscription`. This keeps your subscription revenue safe while allowing the agent to handle low-risk tasks autonomously.

Multi-agent support routing with Recharge tools

The `list_billing_charges` and `list_subscription_orders` tools expose financial details that require specialized handling. With the OpenAI SDK, you can build a triage agent that looks up order history and hands the conversation off to a billing-specific agent. This multi-agent setup keeps your code modular. The billing agent gets exclusive access to `get_order`, while a general support agent manages basic shipping queries using `list_shipping_addresses`.

Tracing Recharge API calls on the OpenAI dashboard

The `get_customer` and `list_subscriptions` tools provide the raw data your agents need to resolve customer issues. When your agent queries these endpoints via the MCP Server, every single tool call is logged directly to your OpenAI developer dashboard for deep tracing. If an agent fails to locate a customer using `list_customers`, you can inspect the exact payload sent to the Recharge API. This visibility makes debugging automated support workflows incredibly fast.

Setup guide

Set up Recharge 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. 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. 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 Recharge tools at runtime.

  3. 3

    Create your Agent

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

  4. 4

    Run the agent

    Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Recharge 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="Recharge Agent",
            instructions="You have access to Recharge tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Recharge. 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.

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 Recharge MCP in OpenAI Agents SDK

Install the `openai-agents` package and initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass the server instance directly into your Agent constructor's `mcp_servers` list to auto-discover all eleven Recharge tools.
Yes, but you should configure guardrails for destructive actions. While the agent can freely run `list_products` to show catalog items, you should restrict `cancel_subscription` behind a verification step.
The SDK relies on Vinkius to handle the core connection, but you should design your agent loops to handle potential API throttling. If your agent calls `list_subscription_orders` too rapidly, Vinkius manages the queue to keep your token active.
You can use `update_subscription` alongside `list_shipping_addresses` to modify customer shipping destinations. The agent reads the existing address and writes the update back to Recharge.
This server processes sensitive customer details, billing charges, and shipping addresses. Vinkius runs the integration in isolated, zero-trust V8 sandboxes, meaning your customer data is never stored or used to train OpenAI models.

Start using the Recharge MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 11 tools

We've already built the connector for Recharge. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 11 tools are live and waiting. You're up and running in seconds.

Vinkius runs on Claude Claude
Vinkius runs on ChatGPT ChatGPT
Vinkius runs on Cursor Cursor
Vinkius runs on Gemini Gemini
Vinkius runs on Windsurf Windsurf
Vinkius runs on VS Code VS Code
Vinkius runs on JetBrains JetBrains
Vinkius runs on Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.