How to Query Shopify Data with Claude / Cursor via MCP (Shopify MCP Server Setup)

See everything Query Streams can do beyond this guide Get Started Free

Supports

+more

Live Data

Replace exports with on-demand SQL

Excel Sheets

BI & AI Analytics

Ask Nova, get SQL + charts

Meet Nova

Database REST API

One key per partner. No credentials shared.

Build an API

+more

Automation

Scheduled sync to 6+ platforms

Explore

+more

API to SQL

Query APIs with SQL, no code

Explore

+more

AI Database MCP

Claude, Cursor, ChatGPT & Grok talk to your data

Connect AI

Query Streams is a secure, real-time data integration platform that brings every database and SaaS API in your account into Claude, Cursor, ChatGPT, and Grok — through a single MCP key with no firewall changes. This guide walks through the shopify mcp path specifically, so your AI tool can answer plain-English questions about orders, customers, products, inventory, fulfillments, and refunds without you exporting reports out of the Shopify admin or stitching together GraphQL Admin API calls. The Network Agent pulls Shopify Admin API data into a local DuckDB cache, so the LLM sees clean SQL surfaces (orders, line_items, customers, products, variants, transactions, fulfillments) instead of raw REST envelopes — and the read-only Admin scope means this is the analytics + ops complement to the official Shopify Storefront MCP, not a replacement for it. Learn more at QueryStreams.com and sign up for free to start asking your AI tool real Shopify Admin questions.

What the Query Streams Shopify MCP server gives you

Other “Shopify MCP” servers on the open-source landscape connect the AI tool directly to the Shopify Admin REST or GraphQL API and push raw resource fetches at it. That works, but it pushes a Shopify private app token into your AI client’s config, leaves the LLM staring at REST envelopes and GraphQL types instead of SQL, scopes the AI tool to only Shopify, and gives you no audit trail of what the AI actually asked. The Query Streams shopify mcp server solves a wider problem: one key, every connector, full audit trail, the agent normalises Shopify Admin data into SQL surfaces, and the AI tool never holds your Shopify credentials.

How it works without opening firewall ports

The Query Streams Network Agent installs once on any machine with internet access (the Shopify Admin API is reachable from anywhere) and dials one outbound TLS link to the cloud; when Claude or Cursor asks a question, the agent calls the Shopify Admin API and caches the response in a local DuckDB so the AI sees clean SQL surfaces — orders, line_items, customers, products, variants, inventory_levels, transactions, fulfillments — instead of REST envelopes, while nothing inbound is ever exposed and the AI tool never sees your Shopify private app token, store domain, or API version. how the outbound-only connection works →

The MCP key you give Cursor or Claude is scoped (read / analyze / execute), revocable at any time, and rate-limited per-key. The AI tool calls these MCP tools to do its work:

Why Schema Intelligence makes Query Streams MCP different

Most “MCP for Shopify” servers in the open-source landscape hand your AI tool the same field reference Shopify publishes for developers — or worse, the raw information_schema of whatever cache they keep. Field names. Data types. Maybe a primary key. The LLM is left to guess that total_price is stored as a STRING and needs to be cast to DOUBLE for arithmetic, that financial_status is an enum of pending / authorized / partially_paid / paid / partially_refunded / refunded / voided, or that tags is a comma-delimited string that needs flattening to a list. That’s why the first SQL most LLMs write against a bare Shopify schema is wrong — not because the LLM is bad, but because it doesn’t have the data it needs to be right (and “SUM is null because total_price is a string” is the kind of failure mode that becomes a wasted afternoon).

Query Streams MCP returns that same cached Shopify schema enriched with what we call Schema Intelligence (SI) — AI-curated metadata that’s generated by running profiling queries against your actual Shopify data before the AI client ever asks. When SI is enabled on the Shopify connector, every schema tool the AI calls (qs_get_connector_schema, qs_get_table_schema, qs_profile_table, qs_get_relationships) returns the bare cached schema plus six layers of curated knowledge. The LLM stops guessing.

To make this concrete, here is what the AI client gets back from a single qs_get_table_schema call against the Shopify connector’s orders table — the canonical Shopify fact table that drives 80% of analytics questions — first without Schema Intelligence, then with it.

The six layers Schema Intelligence adds

Each layer addresses a class of question the LLM would otherwise guess at. The opt-in SI profiling pass runs against your Shopify data without changing your schema or writing to your store, and refreshes incrementally when you add a new metafield definition. what Schema Intelligence adds and how it stays current →

Same prompt, different SQL

The proof is in the SQL the AI tool actually writes. Same Cursor session, same Claude model, same prompt — “What’s our revenue and AOV by month for the last 12 months, only paid orders, in USD?” Without Schema Intelligence the LLM has to guess. With it, the LLM knows total_price is a STRING that needs casting, the financial_status enum value is 'paid' not 'completed', and multi-currency stores need a currency filter.

Query Streams MCP vs Shopify Storefront MCP

Shopify ships an OFFICIAL MCP surface called Shopify Storefront MCP. It exposes the storefront API — catalog, products, collections, public-facing customer data — so AI shopping assistants can help buyers browse products, get recommendations, and check stock visibility. It’s well-designed for buyer-facing AI experiences. It does not see admin / ops / financial data. Query Streams Shopify MCP is the inverse: a read-only Admin API surface for the operations, analytics, finance, and customer-support side of Shopify. The two MCP servers solve different problem shapes — here’s how they line up.

The two MCP servers coexist well, and many Shopify Plus organisations deploy both. Use Shopify Storefront MCP for buyer-facing AI shopping experiences — AI agents that help shoppers browse catalog, get product recommendations, or answer “do you have this in my size?” Use Query Streams Shopify MCP for AI tools that talk to your team — ops, finance, support, and analytics workflows that need orders, transactions, fulfillments, customer lifetime value, inventory levels, refunds, discount codes, and gift cards alongside the rest of your business data. Different audiences, different scopes, both read-only — they complement each other rather than compete.

MCP not for you? Try Nova AI instead.

Skip the JSON config entirely: Nova AI is built into the Query Streams web portal and answers the same plain-English Shopify Admin questions — revenue by product, fulfillment SLAs, cohort retention — across every connector you’ve added, with the same agent, read-only enforcement, and Schema Intelligence, no MCP plumbing.

Meet Nova AI

Prerequisites

Before you start, make sure you have:

1. A free Query Streams account at my.querystreams.com.
2. The Query Streams Network Agent installed on a machine with internet access — see Download the Query Streams Agent. The Shopify Admin API is reachable from anywhere, so the agent doesn’t need to live on a specific network.
3. A Shopify store connector configured against the agent — see the existing API Connector Setup guides for private app pairing. The agent holds the Shopify private app token and your store domain; the AI tool never touches either of them. Each store you want to query is a separate connector, so a multi-store account just adds connectors one at a time.
4. Any MCP-capable AI client. We’ll show Cursor, Claude Desktop, ChatGPT, and Grok in this guide; if you use Windsurf, Zed, Continue, Cline, VS Code Copilot, Codex, or Goose, the config block is essentially the same.
5. Five minutes.

Step 1: Generate an MCP key in Query Streams

Sign in to Query Streams and open the MCP page (or sign in first at my.querystreams.com and click MCP in the left navigation). Click Generate key, give the key a recognizable name (something like cursor-laptop or claude-desktop), and pick the scopes you want this key to have:

• read — the AI can browse connectors and read schema. Required for everything else.
• analyze — the AI can profile tables and discover relationships (sample values, distributions, semantic types). Optional but strongly recommended for ecommerce work, where understanding the shape of your order data and money-column semantics (string-stored prices, multi-currency, enum statuses) matters.
• execute — the AI can actually run SQL. Without this, the AI is read-only against schema metadata only.

For a typical “let Claude analyse my Shopify Admin data” workflow, all three scopes are appropriate. For a key you’re handing to a teammate or a less-trusted client, drop execute and let them browse only. You can revoke any key at any time from the same page; the AI client will see MCP_KEY_REVOKED on its next call and stop working immediately. There’s no propagation delay.

Copy the key now — Query Streams shows it once, then stores only a hash. If you lose it, generate a new one. The key looks like qsmcp_ followed by 48 random characters and is what your AI client sends in the X-MCP-Key request header.

Step 2: Add Query Streams MCP to your AI client

The configuration is the same shape across every MCP-capable client — an MCP server entry pointing at https://mcp.querystreams.com with your key in the X-MCP-Key header. Pick your client below.

Cursor ~/.cursor/mcp.json

// Edit ~/.cursor/mcp.json
{
  "mcpServers": {
    "querystreams": {
      "url": "https://mcp.querystreams.com",
      "headers": {
        "X-MCP-Key": "qsmcp_PASTE_KEY_HERE"
      }
    }
  }
}

Claude Desktop claude_desktop_config.json

// Settings → Developer → Edit Config
{
  "mcpServers": {
    "querystreams": {
      "url": "https://mcp.querystreams.com",
      "headers": {
        "X-MCP-Key": "qsmcp_PASTE_KEY_HERE"
      }
    }
  }
}

ChatGPT Apps & Connectors

// Settings → Apps & Connectors → Add MCP
Server URL  https://mcp.querystreams.com
Auth header X-MCP-Key
Header value qsmcp_PASTE_KEY_HERE

// Requires a paid ChatGPT plan
// (Plus / Pro / Team / Enterprise).

Grok Remote MCP Tools

// Grok → Settings → Tools
{
  "mcp_servers": [{
    "name": "querystreams",
    "url": "https://mcp.querystreams.com",
    "auth_header": "X-MCP-Key",
    "auth_value": "qsmcp_..."
  }]
}

Restart your AI client. On its next start it will discover the eight Query Streams MCP tools listed above and surface them in its tool palette. In Cursor and Claude Desktop you can verify by typing “list connectors” — the AI should call qs_list_connectors and return your Shopify store(s) (each store appears as its own connector if you’ve paired multiple) along with anything else you have configured.

Step 3: Ask the AI a Shopify question

You don’t write SQL — the AI does. You ask a question, the AI picks the right MCP tool, the agent runs the query against your cached Shopify Admin data, and the answer comes back as text plus tables. Three example prompts to try first:

The first time the AI calls a tool, your client may pop up a confirmation prompt asking you to approve the tool call — that’s MCP’s standard consent flow, not anything Query Streams adds. Approve once and the AI proceeds with the rest of the conversation freely. You can revisit the consent at any time in your client’s settings.

Frequently asked questions

Get started

Related guides: Download the Query Streams Agent | API Connector Setup | All MCP Server guides | Nova AI text-to-SQL

Category: MCP Server

Tags: mcp, claude, cursor, shopify, api-connector, ecommerce, shopify-admin, shopify-storefront-mcp, multi-store, read-only-mcp

Meta Description: Query Shopify Admin data with Claude or Cursor via MCP. Cached SQL surfaces, multi-store, no firewall holes. Free.