How do I get an Access Token for GoCardless?

Log in to your GoCardless dashboard, navigate to Developers > Access Tokens, and you can generate a new token for either Sandbox or Live use there.

What is a 'Mandate' in GoCardless?

A mandate is an authorization from your customer that allows you to collect payments from their bank account automatically in the future.

In what units should I provide the payment amount?

The API uses minor units for currency. For example, to collect $1.00 USD (or £1.00 GBP), you must provide the value 100 (cents/pence).

Can I test this without using real money?

Yes! Use the 'sandbox' environment by setting the 'Environment' credential and providing a Sandbox Access Token from your GoCardless account.

GoCardless MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: GoCardless
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect GoCardless through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

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 pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to GoCardless "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in GoCardless?"
    )
    print(result.data)

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 GoCardless MCP Server

Connect your GoCardless merchant account to any AI agent to automate your direct debit payments and customer mandates through the Model Context Protocol (MCP). GoCardless is the global leader in bank-to-bank payments, simplifying the collection of recurring and one-off payments. This MCP server enables you to retrieve customer records, track mandate authorizations, manage payment collections, and monitor bank payouts directly through natural conversation.

Pydantic AI validates every GoCardless tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

Key Features

Customer & Bank Oversight — List all customers registered in your system and fetch detailed profile and bank account metadata instantly.
Mandate Management — Access and track customer authorizations (mandates) to ensure you have the legal right to collect payments.
Payment Orchestration — List all direct debit collections, track their status (confirmed, failed), and programmatically initiate new payments against active mandates.
Subscription Insights — Retrieve active and inactive recurring payment plans to understand your predictable revenue health.
Payout Tracking — Access a complete list of funds being sent from GoCardless to your own bank account for easy reconciliation.
Refund Visibility — Monitor processed refunds and reversed payments to maintain an accurate financial audit trail.
Real-time Synchronization — Keep your bank-to-bank payment data accessible to your AI assistant without leaving your primary workspace.

The GoCardless MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI 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 GoCardless to Pydantic AI via MCP

Follow these steps to integrate the GoCardless MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from GoCardless with type-safe schemas

Why Use Pydantic AI with the GoCardless MCP Server

Pydantic AI provides unique advantages when paired with GoCardless through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your GoCardless integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your GoCardless connection logic from agent behavior for testable, maintainable code

GoCardless + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the GoCardless MCP Server delivers measurable value.

Type-safe data pipelines: query GoCardless with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple GoCardless tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query GoCardless and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock GoCardless responses and write comprehensive agent tests

GoCardless MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect GoCardless to Pydantic AI via MCP:

create_new_payment

Initiate a collection

get_account_details

Get account identity

get_customer_details

Get customer metadata

get_mandate_status

Check mandate details

get_payment_details

Get payment metadata

list_direct_debit_payments

List all payments

list_merchant_payouts

List bank payouts

list_payment_customers

List all customers

list_payment_mandates

List active mandates

list_payment_refunds

List reversed payments

list_recurring_subscriptions

List recurring plans

verify_api_connection

Check connection

Example Prompts for GoCardless in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with GoCardless immediately.

"List all my payments that are currently 'pending_submission'."

"Check the status of mandate 'MD12345'."

"Show me the last 3 payouts sent to my bank account."

Troubleshooting GoCardless MCP Server with Pydantic AI

Common issues when connecting GoCardless to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

GoCardless + Pydantic AI FAQ

Common questions about integrating GoCardless MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your GoCardless MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.