Agentic Commerce Readiness MCP server
{
"mcpServers": {
"expandingweb-agentic-commerce-readiness": {
"type": "http",
"url": "https://expandingweb.com/mcp"
}
}
}{
"mcpServers": {
"expandingweb-agentic-commerce-readiness": {
"type": "http",
"url": "https://expandingweb.com/mcp"
}
}
}{
"mcpServers": {
"expandingweb-agentic-commerce-readiness": {
"type": "http",
"url": "https://expandingweb.com/mcp"
}
}
}{
"servers": {
"expandingweb-agentic-commerce-readiness": {
"type": "http",
"url": "https://expandingweb.com/mcp"
}
}
}{
"mcpServers": {
"expandingweb-agentic-commerce-readiness": {
"type": "http",
"url": "https://expandingweb.com/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.0.0
What it does
A Magento 2 / Adobe Commerce module that runs eight readiness checks against your store to assess how well it supports AI agents accessing product data. It also counts incoming traffic from AI crawlers (GPTBot, ClaudeBot, PerplexityBot, and others) and displays results in the admin dashboard.
- Check whether your store's robots.txt, structured data, and UCP profile are configured correctly for AI agents to browse and understand your products.
- Monitor daily traffic from AI crawlers to see which AI systems are accessing your storefront.
- Diagnose why your products may not appear in AI shopping assistants by reviewing technical verdicts for each of eight checks.
Tools this server exposes
| Tool | Does |
|---|---|
| readiness_scan | Runs eight checks against your Magento store (UCP profile, MCP endpoint, robots.txt policy, edge serving, crawl limits, llms.txt file, product structured data, |
| agent_traffic_counter | Tracks incoming requests from known AI agent user-agents (GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot, ChatGPT-User, Claude-User, Applebot-Extended, Amazonb |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.