How to Use the Getpaid MCP in Mastra AI

Q: How can I use Mastra AI with Getpaid to handle a failed payment?

Your Mastra agent can use listbillingpayments to find the failed charge. Then, use Mastra's workflow logic to trigger a notification, retry the charge later, or prompt the customer for a new payment method.

Q: Does the Getpaid MCP server support Mastra AI's human-in-the-loop approval?

Yes. You can configure requireToolApproval in your Mastra agent for sensitive operations like refundbillingpayment. This will pause the workflow and wait for a human to approve the refund before the Getpaid tool is executed.

Automate complex billing logic. Build resilient payment workflows that handle retries and failures using Mastra AI and Getpaid.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Getpaid MCP to Mastra AI

Create your Vinkius account to connect Getpaid to Mastra 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 Getpaid with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Failsafe Refund Processes

A customer requests a refund. Your Mastra AI agent first calls `get_payment_details` to check the transaction status and amount. This prevents duplicate refunds on already-processed payments. Using Mastra's workflow engine, you add conditional logic. If the payment is eligible, the agent calls `refund_billing_payment`. If that API call fails, Mastra's built-in exponential backoff retries it automatically, ensuring the refund goes through.

Automate Subscription Management

You can build an agent that monitors for failed subscription payments. The workflow starts by calling `list_billing_payments` with a 'failed' status filter. For each failed payment, it uses `get_customer_details` to find the customer's contact info. Then, your agent can trigger a dunning email. After a few days, it checks again. If the payment is still outstanding, it could be configured to automatically cancel their plan using another tool. This entire process runs reliably in the background.

Resilient Checkout Creation with this MCP Server

When your system needs to generate a payment link, things can go wrong—network hiccups, API rate limits. Your Mastra AI agent starts by calling `create_checkout_session`. If the Getpaid API is temporarily down, your agent first runs `verify_api_connection`. Mastra's engine can be configured to wait and retry the `create_checkout_session` call once the connection is restored. This makes your checkout process much more durable.

Setup guide

Set up Getpaid MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Getpaid tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "getpaid-mcp-client",
  servers: {
    "getpaid-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Getpaid Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Getpaid tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Getpaid transactions"
);
console.log(result.text);

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 Getpaid. 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 Getpaid 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 Getpaid MCP in Mastra AI

Your Mastra agent can use `list_billing_payments` to find the failed charge. Then, use Mastra's workflow logic to trigger a notification, retry the charge later, or prompt the customer for a new payment method.

Absolutely. For example, you can build a workflow where an agent uses `get_customer_details`, then `list_billing_invoices` to check for overdue payments, and finally sends a reminder if any are found. Mastra handles the state between each step.

Yes. You can configure `requireToolApproval` in your Mastra agent for sensitive operations like `refund_billing_payment`. This will pause the workflow and wait for a human to approve the refund before the Getpaid tool is executed.

It exposes 12 tools for managing the entire Getpaid billing lifecycle. This includes creating checkouts, fetching customer and payment data, listing invoices, and processing refunds.

The server acts as a secure pass-through. It doesn't store any of the customer or payment metadata it fetches. Each request is handled in an ephemeral, sandboxed environment that is destroyed after the request completes, leaving no trace of your data.

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