How to Use the Salesforce Commerce Cloud MCP in LlamaIndex

Q: How do I index Salesforce Commerce Cloud data using LlamaIndex?

You connect the MCP server using llama-index-tools-mcp and load the tools into your agent. The framework runs sfproductsbyfamily or sfpricebookentries to pull catalog data and ingest it into your vector store.

Q: Can I use LlamaIndex to search Salesforce Commerce Cloud orders semantically?

Yes, by indexing the outputs of sfsearchorders and sforderitems. LlamaIndex allows your agent to query historical transactions using natural language, mapping user intent to specific order numbers.

Q: How does the Salesforce Commerce Cloud MCP Server handle real-time pricing updates in LlamaIndex?

The agent calls sfpricebookentries to fetch current pricing directly from Salesforce before answering a query. This ensures the vector index doesn't serve stale pricing data to your customers.

Q: Can I filter which tools are available in the LlamaIndex MCP adapter?

Yes, you can use the allowedtools filter in the LlamaIndex MCP adapter to restrict the agent. For example, you can expose only sfsearchproducts while blocking write tools like sfupdateproduct.

Q: How is my Salesforce Commerce Cloud order data secured during indexing?

All transaction logs and order summaries retrieved by sfsearchorders are processed locally within your memory space. Vinkius handles the underlying authentication tokens securely, ensuring your sensitive customer purchase history never leaks.

Index your Salesforce Commerce Cloud catalog and order data directly into LlamaIndex vector stores for semantic search.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index catalogs with this LlamaIndex MCP Server

`sf_products_by_family` pulls active products from specific categories so LlamaIndex can chunk and index them into your local vector store. This turns your raw catalog structure into a searchable knowledge base for RAG applications. When users query your agent about product availability, the index matches the semantic intent against live data retrieved by `sf_search_products`. You get accurate answers grounded in actual SKU records instead of model hallucinations.

Query active price books semantically

`sf_pricebook_entries` extracts unit prices and active statuses from your specified price books to build a pricing-aware index in LlamaIndex. The framework uses this structured data to answer complex customer queries about regional discounts or tier pricing. Running `sf_list_pricebooks` first lets the index map the relationship between standard and custom price books. Your agent queries this mapping to ensure it pulls the correct active price for each customer tier.

Analyze order history using semantic search

`sf_search_orders` retrieves confirmed customer transactions by account name or order number to populate your historical order index. LlamaIndex searches these records to identify purchase trends or flag recurring fulfillment issues. To get granular details, the framework calls `sf_order_items` to index individual line items and total prices. This lets your agent answer complex questions about what specific accounts bought over time.

Setup guide

Set up Salesforce Commerce Cloud MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Salesforce Commerce Cloud MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Salesforce Commerce Cloud tools.",
)
response = await agent.run("List recent Salesforce Commerce Cloud data")

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 LlamaIndex

You connect the MCP server using `llama-index-tools-mcp` and load the tools into your agent. The framework runs `sf_products_by_family` or `sf_pricebook_entries` to pull catalog data and ingest it into your vector store.

Yes, by indexing the outputs of `sf_search_orders` and `sf_order_items`. LlamaIndex allows your agent to query historical transactions using natural language, mapping user intent to specific order numbers.

The agent calls `sf_pricebook_entries` to fetch current pricing directly from Salesforce before answering a query. This ensures the vector index doesn't serve stale pricing data to your customers.

Yes, you can use the `allowed_tools` filter in the LlamaIndex MCP adapter to restrict the agent. For example, you can expose only `sf_search_products` while blocking write tools like `sf_update_product`.

All transaction logs and order summaries retrieved by `sf_search_orders` are processed locally within your memory space. Vinkius handles the underlying authentication tokens securely, ensuring your sensitive customer purchase history never leaks.

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