How to Use the Salesforce Commerce Cloud MCP in Mastra AI

Q: Can Mastra AI automatically retry failed catalog updates in Salesforce Commerce Cloud?

Yes. When your agent calls sfupdateproduct and it fails, Mastra's workflow can be configured to retry the operation several times. This makes your catalog management scripts much more robust.

Q: How can I check the contents of a specific order?

First, find the order using sfsearchorders with an order number. Once you have the order ID, pass it to the sforderitems tool. It will return every line item, including product names, quantities, and prices.

Build resilient, automated e-commerce workflows for Salesforce Commerce Cloud with Mastra AI. Handle failures, retries, and conditional logic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Salesforce Commerce Cloud MCP to Mastra AI

Create your Vinkius account to connect Salesforce Commerce Cloud to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Salesforce Commerce Cloud with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate Order Fulfillment Workflows

Build a background agent that processes orders without manual intervention. Your Mastra AI workflow can poll for new orders using `sf_orders_by_status`. When it finds an 'Activated' order, it can use `sf_order_items` to get the line items and pass them to your shipping or ERP system. The point is reliability. If a downstream API fails, Mastra's built-in retry engine can try again with exponential backoff. You can build conditional logic to handle different order types or flag orders for manual review, all within one workflow.

Run Reliable Bulk Catalog Updates

Updating a product line shouldn't be a manual, error-prone task. Create a Mastra AI agent that gets every product in a category with `sf_products_by_family`. The agent can then loop through the list, calling `sf_update_product` on each one to change its description or family. This process is much safer than a simple script. Mastra's workflow engine can run these updates as a transaction, and its conditional logic prevents errors, like trying to update a product that doesn't exist. You can even add a `requireToolApproval` step so a human has to sign off on the bulk change.

Reliably Sync Price Books via your MCP Server

Keep your pricing consistent across systems. A Mastra AI agent can use `sf_list_pricebooks` to find the correct price book ID, then fetch all current prices with `sf_pricebook_entries`. This gives you a complete snapshot of your pricing data. Your workflow can then compare these prices to an external source of truth. If a price needs to be changed, you can queue an update. Because this is a sensitive operation, you can use Mastra AI's human-in-the-loop feature to require a manager's approval before any prices are actually modified in Salesforce.

Setup guide

Set up Salesforce Commerce Cloud 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 Salesforce Commerce Cloud 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: "salesforce-commerce-cloud-mcp-client",
  servers: {
    "salesforce-commerce-cloud-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Salesforce Commerce Cloud 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 Salesforce. 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 Salesforce Commerce Cloud 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 Salesforce Commerce Cloud MCP in Mastra AI

Use Mastra AI's workflow engine. It provides automatic retries and conditional branching out of the box. Your agent can call tools on this MCP server, and if a network error or API limit is hit, Mastra will handle it gracefully.

Yes. When your agent calls `sf_update_product` and it fails, Mastra's workflow can be configured to retry the operation several times. This makes your catalog management scripts much more robust.

Absolutely. For sensitive operations like changing prices or deactivating products with `sf_update_product`, you can set `requireToolApproval` in your Mastra AI agent. The workflow will pause until a human signs off.

First, find the order using `sf_search_orders` with an order number. Once you have the order ID, pass it to the `sf_order_items` tool. It will return every line item, including product names, quantities, and prices.

Your Mastra AI agent runs in your own environment. It sends specific, structured requests to the Vinkius MCP server, which executes the Salesforce call in a dedicated, single-use sandbox. Only the data for that one operation—like product SKUs or price book entries—is processed, and the environment is erased immediately after.

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