How to Use the Salesforce Commerce Cloud MCP in AutoGen

Q: Can I restrict write access for specific AutoGen agents in Salesforce Commerce Cloud?

Yes, you can assign read-only tools like sfsearchproducts to your customer-facing agents, while reserving sfupdateproduct exclusively for your admin or manager agents.

Q: Can the agents resolve pricing discrepancies automatically?

Yes, by setting up a debate where one agent queries sforderitems and another queries sfpricebookentries. The agents compare the values and use sfupdateproduct to align catalog details if authorized.

Let AutoGen agents debate and coordinate complex Salesforce Commerce Cloud catalog updates and order audits.

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 AutoGen

Create your Vinkius account to connect Salesforce Commerce Cloud to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Audit catalogs using this AutoGen MCP Server

`sf_update_product` executes catalog modifications only after your AutoGen billing and catalog agents reach a consensus on the changes. One agent drafts the description update while another verifies that the active status matches current inventory rules. This multi-agent debate prevents accidental catalog corruption on your storefront. The agents discuss the proposed changes in a structured loop before committing the final API call to Salesforce.

Audit transaction pricing with multi-agent debate

`sf_order_items` retrieves the specific line items of an order so your auditing agent can check the unit prices against the price books. A separate pricing agent runs `sf_pricebook_entries` to verify that the active prices match the store rules. If the agents find a mismatch, they negotiate a resolution or flag the order for manual review. This consensus-driven approach keeps your storefront pricing consistent without manual auditing.

Manage fulfillment workflows through agent coordination

`sf_orders_by_status` allows your fulfillment tracking agent to identify draft orders that require immediate activation. The tracking agent communicates these order numbers to a coordinator agent to prepare them for shipping. When specific accounts require lookups, the agents call `sf_search_orders` to retrieve transaction details and account names. The entire conversation is managed asynchronously, ensuring no order is processed without verification.

Setup guide

Set up Salesforce Commerce Cloud MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Salesforce Commerce Cloud tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Salesforce Commerce Cloud_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Salesforce Commerce Cloud data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Salesforce Commerce Cloud_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Salesforce Commerce Cloud data")
    print(result.messages[-1].content)

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 AutoGen

You register the tools with your agent group, allowing different agents to call different tools. For instance, a catalog agent might call `sf_products_by_family` while a pricing agent calls `sf_pricebook_entries` to resolve a product classification dispute.

Yes, you can assign read-only tools like `sf_search_products` to your customer-facing agents, while reserving `sf_update_product` exclusively for your admin or manager agents.

The AutoGen MCP adapter automatically converts the JSON schemas of tools like `sf_list_pricebooks` and `sf_order_items` into the format required by the framework. You do not need to write manual wrappers.

Yes, by setting up a debate where one agent queries `sf_order_items` and another queries `sf_pricebook_entries`. The agents compare the values and use `sf_update_product` to align catalog details if authorized.

Your price books and product codes are handled within the secure Vinkius sandbox environment. The raw API credentials used by `sf_list_pricebooks` are never exposed in the multi-agent chat logs or sent to the LLM.

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