How to Use the GoCardless MCP in OpenAI Agents SDK

Q: How do I initialize the GoCardless MCP Server using the OpenAI Agents SDK?

Install openai-agents and instantiate MCPServerStreamableHttp pointing to your Vinkius MCP endpoint. Pass this server instance in the mcpservers list when creating your Agent to enable auto-discovery.

Q: Can an OpenAI Agents SDK agent stop a payment in GoCardless?

Yes. The agent can call stoppendingpayment if it detects a cancellation request or a dispute. It must trigger this action before the banking clearing cycle locks the transaction.

Q: What happens if a bank mandate is rejected?

The agent checks the authorization status via getmandatedetails. If the mandate is inactive or rejected, the agent can notify the customer to re-submit their bank details.

Automate bank debit collection and mandate tracking securely with the OpenAI Agents SDK and this managed GoCardless MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GoCardless MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Direct Debits Safely with OpenAI Agents SDK

The `create_new_customer` and `list_active_mandates` tools let your OpenAI Agents SDK agent build verified payer profiles programmatically. It sets up the bank registration flows without you writing manual onboarding logic. Once setup completes, the agent uses `collect_payment` to pull funds directly from the customer's bank account. If a user requests a cancellation, the agent invokes `stop_pending_payment` to halt the transfer before the clearing window closes.

Track Payment States and Handle Clearing Latency

The `get_payment_status` and `list_payment_history` tools allow your agent to monitor bank transfer cycles over multiple business days. Bank transfers take days to clear, so your agent needs to check status updates over time instead of expecting instant confirmation. To keep your internal records synchronized, the agent monitors the ledger using `list_system_events`. When a status changes from pending to failed, your agent can trigger automated dunning workflows or alert account managers immediately.

Audit Customer Portfolios and Creditor Accounts

The `list_account_creditors` and `get_customer_details` tools give your agent visibility into where payouts are routed and who owns each account. Managing multiple bank payouts requires clear visibility into your processing nodes, and these tools provide exactly that. For long-term accounts, the agent runs `list_recurring_payments` to check active subscription schedules. This keeps your finance team updated on projected cash flow without requiring manual spreadsheet exports.

Setup guide

Set up GoCardless 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 GoCardless tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate GoCardless 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="GoCardless Agent",
            instructions="You have access to GoCardless 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 GoCardless. 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 GoCardless 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 GoCardless MCP in OpenAI Agents SDK

Install `openai-agents` and instantiate `MCPServerStreamableHttp` pointing to your Vinkius MCP endpoint. Pass this server instance in the `mcp_servers` list when creating your Agent to enable auto-discovery.

Yes. The agent can call `stop_pending_payment` if it detects a cancellation request or a dispute. It must trigger this action before the banking clearing cycle locks the transaction.

The SDK relies on standard HTTP error propagation. When the server returns a rate limit status, your agent receives the error directly, allowing you to implement backoff logic in your execution loop.

The agent checks the authorization status via `get_mandate_details`. If the mandate is inactive or rejected, the agent can notify the customer to re-submit their bank details.

This integration accesses customer bank routing numbers and mandate identifiers. Vinkius runs the server inside a zero-trust, ephemeral V8 isolate sandbox, ensuring your financial payloads are never persisted or exposed to external runtimes.

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