How to Use the Checkout.com MCP in Mastra AI

Q: How do I use the Checkout.com tools with a Mastra AI agent?

After installing @mastra/mcp, instantiate the MCPClient with your Vinkius server URL. Then, call mcpClient.listTools() and spread the result into your agent's tool configuration. Mastra handles the rest.

Q: Does the Checkout.com MCP Server support human-in-the-loop with Mastra AI?

It does. Mastra AI's requireToolApproval option works with this MCP Server. You can configure it so that critical actions like refundpayment or deleteinstrument require a person to approve them before the agent executes the call to Checkout.com.

Q: What's the best way to manage vaulted cards from Checkout.com in a Mastra AI workflow?

Use createinstrument to save a card and getinstrument to retrieve it for future payments. Your agent can use updateinstrument for changes, and deleteinstrument to remove it, building a complete lifecycle management workflow.

Build resilient payment workflows for Checkout.com with Mastra AI. Automate captures, retries, and refunds with conditional logic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Checkout.com MCP to Mastra AI

Create your Vinkius account to connect Checkout.com 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 Checkout.com with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Payment Capture and Voiding

The `request_payment` tool initiates a charge, and your Mastra AI agent can decide what to do next. You can use `capture_payment` to settle the funds or `void_payment` to cancel the hold if certain conditions aren't met. This is perfect for building automated order fulfillment workflows. If inventory is low, your agent can automatically void the payment authorization, preventing a charge for an out-of-stock item without any manual work.

Build Resilient Workflows with Mastra AI

Use the `create_instrument` tool to save a customer's payment method. Mastra AI's built-in retry logic means if the initial API call fails, your agent automatically tries again with exponential backoff. You can also build conditional logic. For example: if `get_instrument` shows a card is expiring, the agent can trigger a notification. If `delete_instrument` fails, it can flag the account for manual review.

Create Complex Refund and Reconciliation Logic

The `refund_payment` tool lets your agent process returns. But with Mastra AI, you can build a whole workflow around it. For instance, before refunding, your agent can use `get_payment_details` to check the original transaction date. This prevents duplicate refunds and gives you a solid audit trail for your payment operations, all powered by your MCP server.

Setup guide

Set up Checkout.com 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 Checkout.com 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: "checkoutcom-1-mcp-client",
  servers: {
    "checkoutcom-1-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Checkout.com 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 Checkout.com. 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 Checkout.com 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 Checkout.com MCP in Mastra AI

After installing `@mastra/mcp`, instantiate the `MCPClient` with your Vinkius server URL. Then, call `mcpClient.listTools()` and spread the result into your agent's tool configuration. Mastra handles the rest.

Yes, that's what Mastra AI is built for. You can define workflows where if `request_payment` fails, the agent can retry, try a different instrument using `get_instrument`, or trigger an alert.

It does. Mastra AI's `requireToolApproval` option works with this MCP Server. You can configure it so that critical actions like `refund_payment` or `delete_instrument` require a person to approve them before the agent executes the call to Checkout.com.

Use `create_instrument` to save a card and `get_instrument` to retrieve it for future payments. Your agent can use `update_instrument` for changes, and `delete_instrument` to remove it, building a complete lifecycle management workflow.

Your agent can access transaction records and vaulted instrument identifiers from Checkout.com. The connection is secured end-to-end. Your Mastra agent communicates with the Vinkius MCP server, which runs in a sandboxed environment and uses your unique token for every ephemeral request.

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