How do I get a Client ID and Secret for Getpaid?

Log in to your Getpaid dashboard, navigate to Settings > Integrations, and you can create a new API integration to retrieve your Client ID and Client Secret.

In what units should I provide the payment amount?

The API uses minor units for currency. For example, to charge $1.00 USD, you must provide the value 100 (cents).

Can I process refunds through the agent?

Yes! Use the 'refund_billing_payment' tool and provide the specific Payment ID. You can also specify a custom amount for a partial refund.

How do I check if a checkout session was completed?

Use the 'get_checkout_status' tool with the Checkout ID. The agent will return the current state, such as 'completed', 'pending', or 'expired'.

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

Name: Getpaid
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 Getpaid through 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 Getpaid "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Getpaid?"
    )
    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 Getpaid MCP Server

Connect your Getpaid account to any AI agent to automate your billing, payment processing, and checkout workflows through the Model Context Protocol (MCP). Getpaid is a modern payment platform designed for SaaS, marketplaces, and service businesses to handle global transactions with ease. This MCP server enables you to track payments, manage customer records, and initiate new checkout sessions directly through natural conversation.

Pydantic AI validates every Getpaid tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through 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

Payment Oversight — List all processed payments, fetch detailed metadata including status and timestamps, and monitor revenue flow instantly.
Checkout Automation — Create new checkout sessions for products or services and retrieve secure payment links programmatically.
Refund Management — Process full or partial refunds for captured payments directly from your chat interface.
Customer & Invoice Tracking — Access your billing database, retrieve detailed customer profiles, and monitor generated invoices.
Subscription Insights — List active and inactive recurring billing plans to understand your long-term revenue health.
Webhook Visibility — Monitor configured webhooks to ensure your internal systems are receiving real-time payment notifications.
Real-time Synchronization — Keep your financial operations accessible to your AI assistant without leaving your primary workspace.

The Getpaid 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 Getpaid to Pydantic AI via MCP

Follow these steps to integrate the Getpaid 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 Getpaid with type-safe schemas

Why Use Pydantic AI with the Getpaid MCP Server

Pydantic AI provides unique advantages when paired with Getpaid 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 Getpaid integration code

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

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

Getpaid + Pydantic AI Use Cases

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

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

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

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

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

Getpaid MCP Tools for Pydantic AI (12)

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

create_checkout_session

Initiate checkout

get_account_details

Get account identity

get_checkout_status

Check checkout status

get_customer_details

Get customer metadata

get_payment_details

Get payment metadata

list_billing_customers

List customers

list_billing_invoices

List invoices

list_billing_payments

List all payments

list_billing_subscriptions

List recurring plans

list_payment_webhooks

List webhook configs

refund_billing_payment

Process a refund

verify_api_connection

Check connection

Example Prompts for Getpaid in Pydantic AI

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

"List all payments processed today."

"Create a checkout session for $25.00 USD."

"Refund payment 'pay_98765' for the full amount."

Troubleshooting Getpaid MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Getpaid + Pydantic AI FAQ

Common questions about integrating Getpaid 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 Getpaid MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.