Salesforce Commerce Cloud Agentic MCP
The official Model Context Protocol adapter for Salesforce Commerce Cloud (B2C). Empower your AI agents to seamlessly navigate headless storefronts, manage e-commerce orders, and interact with complex SCAPI/OCAPI endpoints natively.
README
šļø Salesforce Commerce Cloud Agentic MCP
The official Model Context Protocol adapter for Salesforce Commerce Cloud (B2C). Empower your AI agents to seamlessly navigate headless storefronts, manage e-commerce orders, and interact with complex SCAPI/OCAPI endpoints natively.
Headless E-Commerce meets Autonomous AI
Modern storefronts are incredibly complex. This MCP server abstract away the intricacies of Commerce Cloud authentication and rate-limiting. By exposing semantically rich tools, your AI agents can perform real-time inventory checks, orchestrate cart operations, and provide deeply personalized customer insights based on historical order data.
Enterprise Edge Hosting by Vinkius
This server is highly optimized for the Vinkius Edge ecosystem. Hosting your AI tools on Vinkius offers distinct competitive advantages for e-commerce operations:
- Unmatched Speed: E-commerce AI demands fast catalog responses. Vinkius Edge isolates ensure your MCP runs globally, right next to your users, delivering sub-millisecond execution.
- Vinkius Marketplace Integration: Easily share or monetize your custom storefront agents through the Vinkius ecosystem.
- Battle-tested Security: E-commerce data is highly sensitive. The Vinkius runtime isolates your API tokens away from the LLM context window.
Core Toolkit
Agents equipped with this MCP gain the following abilities:
query_catalog: Deep semantic searches across your Commerce Cloud product catalog. Filters by category, availability, and pricing in real-time.manage_orders: Allows the agent to fetch order statuses, trace shipments, and process cancellations or modifications safely.customer_insights: Retrieves comprehensive buyer profiles and transaction histories, enabling the AI to offer bespoke shopping support.
ā” 1-Click Vinkius Deployment
Forget about provisioning servers or managing Docker containers. Vinkius provides free, serverless edge hosting for MCP projects.
Simply run:
npx mcpfusion deploy
Your storefront agent bridge is now live.
š View the Salesforce Commerce Cloud MCP on the Vinkius Marketplace
Developer Setup
If you are extending the capabilities locally via mcpfusion:
npm install
npm run dev
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.