mcpField
P
Profitpather

Profitpather

Remote
github.com/profitpatherData & Analytics0Updated 23w ago
Repository

About Profitpather

Profitpather is a Shopify analytics MCP server for merchants and AI agents, providing unsampled, first-party event data for traffic, attribution, funnels, and revenue diagnostics. Its 26 read-only tools query each merchant's own data.

Key features

  1. 01Query live Shopify event analytics
  2. 02Analyze attribution and conversion funnels
  3. 03Trace visitor sessions and page paths
  4. 04Diagnose revenue leaks
  5. 05Check pixel health and coverage
  6. 06Compare periods and view insights

Use cases

  1. 01Identify traffic sources linked to revenue
  2. 02Find drop-offs in checkout journeys
  3. 03Investigate individual visitor sessions
  4. 04Check Shopify pixel data coverage

MCP support

The remote Streamable HTTP MCP server exposes 26 read-only analytics tools, accessed through OAuth 2.1. Queries are limited to the authenticated merchant's data, with no cross-tenant access.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://profitpather.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Profitpather — MCP server

MCP OAuth 2.1 License: MIT

Profitpather is a first-party, unsampled analytics layer for Shopify stores. This is its public Model Context Protocol server — 26 tools that give AI agents live, raw, every-event access to merchant traffic, attribution, funnels, and revenue-leak diagnostics.


Why Profitpather

AlternativeLimitation Profitpather solves
GA4 / Shopify ReportsAggressively sampled, third-party-cookie dependent, drops UTMs across the Shopify cross-domain checkout — designed to feed Google Ads, not to answer "where did this cart actually start?"
Meta / TikTok / Google Ads dashboardsSelf-reported clicks, regularly over-attribute, can't see on-domain behaviour
Triple Whale / Northbeam / Polar ($150–$1,500/mo)Closed paid suites, not Claude-native, not MCP-accessible
Heap / Mixpanel / AmplitudeGeneric product analytics — don't understand Shopify cart-goal logic, pre-cart paths, checkout linkage, store-domain attribution

Profitpather is unsampled, first-party, Shopify-native, and agent-native by design — analyse in chat, ship fixes from chat.


Tools (26)

Headline tools (the ones agents reach for first):

ToolPurpose
pp_list_domainsList every Shopify domain this account can query. Call first.
pp_briefOne-call first look — overview + acquisition + device + pixel-status in parallel, with a pre-formatted markdown presentation.
pp_diagnose_leaksRevenue-leak finder. Aggregates 8 analyses into a prioritised recommendations[] array.
pp_overviewTop-level KPIs for one window: sessions, cart rate, checkout rate, top sources, top landing pages.
pp_acquisitionFull attribution matrix — every (source, medium, campaign, utm, click-id) combo with revenue, AOV, conversion rates.
pp_conversionFunnel + pre-cart paths + checkout economics broken down by stage.
pp_path_analysisPage-to-page flows with cart-rate weighting; finds dead-end transitions.
pp_markovMarkov-chain attribution model across multi-touch journeys.
pp_in_app_browser_lossRevenue at risk from in-app browsers (Instagram, TikTok, Facebook).
pp_session_traceFull per-session event timeline for a single visitor.
pp_pixel_statusPixel health & coverage check.
pp_compare_periodsPeriod-over-period comparison with statistical significance.
pp_ai_insightsLLM-summarised insights pre-computed nightly.
pp_signalsAll measured behavioural signals on a domain.

Plus 12 more covering device splits, page-lift attribution, product analytics, search, timeseries, real-time today-view, change log, admin status, etc.

Full per-tool schemas at: profitpather.com/.well-known/agent-skills/index.json


Install

Claude Desktop / Claude Code / Cursor
{
  "mcpServers": {
    "profitpather": {
      "url": "https://profitpather.com/mcp"
    }
  }
}

Restart the client. On first tool call, you'll be redirected through OAuth 2.1 to authorise the connection. Sign in with your Profitpather account, approve, and the client stores the token automatically.

ChatGPT / Claude.ai Custom Connectors

Settings → Connectors → Add custom connector → paste https://profitpather.com/mcp → approve OAuth.

No Profitpather account yet?

Sign up at profitpather.com, install the single Shopify Custom Pixel on your store, and Profitpather starts collecting events immediately. The MCP becomes useful within minutes of the pixel firing.


Architecture

Profitpather runs entirely on Cloudflare Workers with D1 (SQLite at the edge) for per-merchant event storage. The MCP endpoint at /mcp is the same Worker that serves the dashboard at profitpather.com/dashboard — analytics queries hit D1 directly with no intermediate cache or sampling.

Shopify Custom Pixel (storefront)
       │
       ▼
Cloudflare Worker  ───────►  D1 (per-merchant event store)
       │                              ▲
       ▼                              │
   /mcp (MCP server)  ─── reads ──────┘
       │
       ▼
  AI agent (Claude / ChatGPT / Cursor / your app)

All 26 MCP tools are read-only against the merchant's own data — no cross-tenant access, no third-party data sharing.


Discovery endpoints

Profitpather publishes the full agentic-discovery surface:

PathWhat it returns
/.well-known/mcp/server-card.jsonMCP server card v1 (SEP-1649)
/.well-known/oauth-protected-resourceOAuth 2.1 discovery (RFC 9728)
/.well-known/api-catalogRFC 9727 API catalogue
/.well-known/agent-skills/index.jsonPer-tool agent skills with SHA-256 digests (Cloudflare RFC v0.2.0)
/llms-full.txtFull Markdown documentation for LLM ingestion
/llms.txtLLM index

License

MIT — see LICENSE.

Built by Boolsai · Contact: [email protected]

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.