How to Use the Gelato MCP in Claude Code

Q: How do I configure the Gelato server in Claude Code?

Run claude mcp add --transport http gelato -- in your terminal. Ensure all flags are placed before the server name to update your /.claude.json file.

Q: Can Claude Code test Gelato API connectivity in CI?

Yes. Add a step in your pipeline that runs verifyapiconnection. If the token fails, the agent returns an error code and halts the deployment.

Q: How do I fetch Gelato product catalogs with Claude Code?

You instruct the agent to execute listproductcatalogs and pipe the output to a local JSON file. It pulls the entire directory for your backend scripts to process.

Q: Can I script Gelato shipping quotes via Claude Code?

The agent runs getshippingquote with your specified parameters. You iterate through multiple addresses to generate a bulk pricing report directly in the terminal.

Q: Does this headless setup log my Gelato order data?

Tools like getorderstatus process exact customer names and tracking numbers. Vinkius routes these requests through stateless execution environments, ensuring no persistent logs retain your fulfillment data.

Manage Gelato print operations directly from your terminal using 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 Gelato MCP to Claude Code

Create your Vinkius account to connect Gelato 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 Gelato with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Gelato Webhooks via MCP Server

The `list_print_webhooks` tool allows Claude Code to dump your current event configurations straight to standard output. You pipe this data into jq or a log file to audit which endpoints are receiving fulfillment updates. When debugging failed deliveries, running `list_print_orders` lets you filter recent transactions from the command line. You bypass the web dashboard entirely and inspect the raw JSON responses for missing fields.

Headless Print Order Execution

Invoking `create_print_order` turns Claude Code into a headless fulfillment engine. You trigger batch orders from a cron job or a GitHub Action by passing the necessary customer and design parameters. If a script misfires, you immediately run `cancel_print_order` from the same terminal session. The agent requires the specific ID and halts the production process before billing occurs.

Automate Shipment Tracking Queries

Calling `get_order_shipments` fetches the active carrier status for any print run. You configure Claude Code to check this endpoint daily and alert your Slack channel if a package stalls in transit. To diagnose specific item issues, `get_order_status` pulls the granular production phase. The agent reads the exact state—whether printed, packed, or shipped—and outputs the result for your automated reporting scripts.

Setup guide

Set up Gelato 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 gelato-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http gelato-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 Gelato 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": {
    "gelato-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 Gelato. 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 Gelato 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 Gelato MCP in Claude Code

Run `claude mcp add --transport http gelato -- ` in your terminal. Ensure all flags are placed before the server name to update your `~/.claude.json` file.

Yes. Add a step in your pipeline that runs `verify_api_connection`. If the token fails, the agent returns an error code and halts the deployment.

You instruct the agent to execute `list_product_catalogs` and pipe the output to a local JSON file. It pulls the entire directory for your backend scripts to process.

The agent runs `get_shipping_quote` with your specified parameters. You iterate through multiple addresses to generate a bulk pricing report directly in the terminal.

Tools like `get_order_status` process exact customer names and tracking numbers. Vinkius routes these requests through stateless execution environments, ensuring no persistent logs retain your fulfillment 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