Analytics MCP server
{
"mcpServers": {
"profitpather": {
"type": "http",
"url": "https://profitpather.com/mcp"
}
}
}{
"mcpServers": {
"profitpather": {
"type": "http",
"url": "https://profitpather.com/mcp"
}
}
}{
"mcpServers": {
"profitpather": {
"type": "http",
"url": "https://profitpather.com/mcp"
}
}
}{
"servers": {
"profitpather": {
"type": "http",
"url": "https://profitpather.com/mcp"
}
}
}{
"mcpServers": {
"profitpather": {
"type": "http",
"url": "https://profitpather.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 0.3.7
What it does
Profitpather is a first-party, unsampled analytics layer for Shopify stores that exposes 26 tools for querying sessions, attribution, funnels, and revenue leaks. It is for Shopify merchants and their AI agents who need raw, unsampled traffic data and conversion diagnostics without sampling or third-party cookie limitations.
- Query attribution across all traffic sources and UTM combinations to see which acquisition channels actually drive revenue and AOV.
- Diagnose revenue leaks by running automated analyses across checkout funnels, in-app browser loss, and dead-end page transitions.
- Trace individual visitor journeys from landing page through cart to checkout using per-session event timelines and Markov-chain multi-touch models.
Tools this server exposes
| Tool | Does |
|---|---|
| pp_list_domains | List every Shopify domain the account can query. |
| pp_brief | One-call overview combining KPIs, acquisition, device splits, and pixel status in formatted markdown. |
| pp_diagnose_leaks | Revenue-leak finder that aggregates eight analyses into a prioritised recommendations array. |
| pp_overview | Top-level KPIs for a time window: sessions, cart rate, checkout rate, top sources, and top landing pages. |
| pp_acquisition | Full attribution matrix showing every source, medium, campaign, and UTM combination with revenue, AOV, and conversion rates. |
| pp_conversion | Funnel analysis with pre-cart paths and checkout economics broken down by stage. |
| pp_path_analysis | Page-to-page flows with cart-rate weighting to identify dead-end transitions. |
| pp_markov | Markov-chain attribution model across multi-touch visitor journeys. |
| pp_in_app_browser_loss | Quantifies revenue at risk from in-app browsers on Instagram, TikTok, and Facebook. |
| pp_session_trace | Full per-session event timeline for a single visitor. |
| pp_pixel_status | Pixel health and coverage check. |
| pp_compare_periods | Period-over-period comparison with statistical significance testing. |
| pp_ai_insights | LLM-summarised insights pre-computed nightly. |
| pp_signals | All measured behavioural signals on a domain. |
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.