How to Use the VTEX Checkout MCP in Claude Code

Q: Can Claude Code run simulations for VTEX Checkout?

Yes. You can execute simulateorder from a Docker container or GitHub Action. The tool handles the complexity of calculating costs and returns the full order structure as clean JSON output.

Q: If I need to create an address for VTEX Checkout, how do I run it?

You call createaddress directly in your shell script. You pass the required data via standard input or environment variables, and the tool returns a success confirmation code.

Q: Does Claude Code help with complex validation for VTEX Checkout?

It does. You write a script that calls simulatepayment and uses grep or jq to parse the resulting JSON output, checking specific fields like 'status' or 'errorcode' to validate the transaction.

Run VTEX Checkout flows in headless CI/CD pipelines with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect VTEX Checkout MCP to Claude Code

Create your Vinkius account to connect VTEX Checkout to Claude Code 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 VTEX Checkout with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Cart Simulations from the CLI

Need to validate checkout logic in a container? You can pipe requests to `simulate_order` and capture the resulting JSON output. This is essential for automated testing that doesn't need a UI or browser. The tool processes mock cart data, calculates taxes and shipping based on stored rules, and outputs the full simulated order payload directly to stdio.

Validate Payment Calls via Claude Code

Running payments in CI/CD is tricky. Use `simulate_payment` to validate payment types against mock data without incurring costs or touching real endpoints. The output confirms if the transaction structure passed validation. You write a simple shell script that calls this tool, captures the exit code, and proceeds with other deployment steps only if the payment simulation was successful.

Fetch Client Data for VTEX Checkout

When setting up backend services, you often need client data first. Pipe a call to `get_client_profile` to pull user details into your script's environment variables. This avoids hardcoding sensitive information. If the required field is missing (like an address), you can programmatically run `create_address`, ensuring the record exists before the main checkout service runs.

Setup guide

Set up VTEX Checkout MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see vtex-checkout-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest VTEX Checkout transactions." It will automatically discover and invoke the available VTEX Checkout tools.

Terminal

claude mcp add --transport http vtex-checkout-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the VTEX Checkout MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "vtex-checkout-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 VTEX. 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 VTEX Checkout 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 VTEX Checkout MCP in Claude Code

You build a script that calls the MCP Server endpoint. The output of `get_orderform` is piped into your script, allowing subsequent commands to process cart data without manual intervention.

Yes. You can execute `simulate_order` from a Docker container or GitHub Action. The tool handles the complexity of calculating costs and returns the full order structure as clean JSON output.

You call `create_address` directly in your shell script. You pass the required data via standard input or environment variables, and the tool returns a success confirmation code.

The server manages order form details, client profile information (addresses), and coupon codes. All interaction is based on structured data payloads passed via the command line.

It does. You write a script that calls `simulate_payment` and uses `grep` or `jq` to parse the resulting JSON output, checking specific fields like 'status' or 'error_code' to validate the transaction.

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