How to Use the GoCardless MCP in Pydantic AI

Q: Can Pydantic AI validate GoCardless direct debit mandates?

Yes, when calling listpaymentmandates, the framework validates every field in the mandate object. This ensures your agent only acts on active, structurally valid customer agreements.

Q: How does Pydantic AI handle connection checks with GoCardless?

The agent uses verifyapiconnection to confirm the gateway is reachable. The response is parsed into a validated model, ensuring the authentication state is exactly what the application expects.

Build type-safe, validated financial agents using Pydantic AI and the 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 Pydantic AI

Create your Vinkius account to connect GoCardless to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute validated payments with Pydantic AI

The `create_new_payment` tool forces all transaction inputs through strict runtime validation schemas. Pydantic AI rejects malformed payment requests before they leave your environment, preventing bad data from hitting the payment network. When collecting funds, the agent calls `get_mandate_status` to ensure the customer's direct debit agreement is fully authorized. If the API returns unexpected data formats, the framework raises a loud validation error instead of failing silently.

Validate recurring subscription schemas automatically

The `list_recurring_subscriptions` tool retrieves active billing plans and parses them directly into typed Python models. Pydantic AI ensures that every subscription ID, amount, and cadence matches your expected data structures. If you need to inspect a specific customer, the agent uses `get_customer_details` to fetch metadata. The framework guarantees that fields like email addresses and country codes conform to strict validation rules before your code processes them.

Reconcile bank payouts using this verified MCP Server

The `list_merchant_payouts` tool returns payout batches that are validated against rigorous financial schemas. Pydantic AI parses these bank transfers, making it impossible for the agent to process corrupted payout amounts. To handle discrepancies, the agent calls `list_payment_refunds` to audit reversed transactions. This strict validation loop ensures your internal ledgers remain perfectly synchronized with GoCardless.

Setup guide

Set up GoCardless MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "gocardless-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to GoCardless tools.",
)

result = await agent.run("List recent GoCardless transactions")
print(result.output)

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 Pydantic AI

Install the slim package with MCP support, then initialize the `MCPToolset` with your Vinkius HTTP endpoint. Pass this toolset directly to your Agent constructor to enable type-safe tools.

The framework immediately raises a validation error at runtime. This prevents your agent from executing decisions based on corrupted or hallucinated API responses.

Yes, when calling `list_payment_mandates`, the framework validates every field in the mandate object. This ensures your agent only acts on active, structurally valid customer agreements.

The agent uses `verify_api_connection` to confirm the gateway is reachable. The response is parsed into a validated model, ensuring the authentication state is exactly what the application expects.

Vinkius runs the server in an ephemeral, zero-trust sandbox, keeping your API keys hidden from the LLM. Refund details fetched via `list_payment_refunds` are validated in memory and never cached, preventing leaks of financial transactions.

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