Moltline Shopify

Check a product CSV, handles, variant matrices and metafield keys.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Product Csv Check: Check a product CSV's header row against Shopify's current columns. FREE. Catches the failure that wastes the most time: a template copied from an out-of-date guide, using column na
  • Url Handle: Turn a product title into a valid, unique Shopify URL handle. FREE. Shopify handles are lowercase, may contain letters, numbers and dashes, and may not contain spaces. Typical input {"titl
  • Variant Matrix: Count the variants a set of options produces, and flag the ceilings. FREE. Option counts multiply, so three modest lists become a number nobody intended. Typical input {"options": {"Si

What data it sees

Do you need an account

No: the server works without sign-in

Check a product CSV, handles, variant matrices and metafield keys. 4 of 6 tools free.

Part of Moltline Studio: 22 hosted MCP servers, 160 tools, 110 of them free — no account, no API key, no signup. Independently audited — MCPize Verified A+.

Direct endpoint: https://mcp.moltlinestudio.com/shopify

How to connect

How to connect Moltline Shopify to Claude

The server address to paste into Claude settings:

https://moltline-shopify--techdpr.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Moltline Shopify to ChatGPT

The server address to paste into ChatGPT settings:

https://moltline-shopify--techdpr.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Moltline Shopify to Cursor

The server address to paste into Cursor settings:

https://moltline-shopify--techdpr.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (6)

Raw names from tools/list. Only developers need these.

product_csv_checkCheck a product CSV's header row against Shopify's current columns. FREE. Catches the failure that wastes the most time: a template copied from an out-of-date guide, using column names Shopify renamed. Typical input {"header_row": ["Handle", "Title", "Body (HTML)", "Variant Price"]} returns {"ok": false, "missing_required": [], "renamed": [{"found": "Handle", "use": "URL handle"}, ...], "unrecognised": [], "verdict": "..."}. Use before an import, on the header row alone. Not for whether the values in the rows are valid — check a handle with url_handle and a metafield key with metafield_key_check. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "header_row must contain at least one column name"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
url_handleTurn a product title into a valid, unique Shopify URL handle. FREE. Shopify handles are lowercase, may contain letters, numbers and dashes, and may not contain spaces. Typical input {"title": "Men's Merino Wool Socks (2-Pack)"} returns {"handle": "mens-merino-wool-socks-2-pack", "valid": true, "changed": true, "collisions": []}. Use when generating handles for an import, or checking one you already have. Not for validating a whole header row — that is product_csv_check. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "title must not be empty"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
variant_matrixCount the variants a set of options produces, and flag the ceilings. FREE. Option counts multiply, so three modest lists become a number nobody intended. Typical input {"options": {"Size": ["S", "M", "L"], "Colour": ["Black", "Navy"]}} returns {"option_count": 2, "variant_count": 6, "within_limits": true, "per_option": {"Size": 3, "Colour": 2}}. Use before building an import file, to find out whether the catalogue needs splitting into several products. Not for validating the resulting CSV's columns — that is product_csv_check. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "options must contain at least one option"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
metafield_key_checkValidate a metafield namespace and key before you define it. FREE. Shopify metafield namespaces and keys are lowercase alphanumerics and underscores; a capital letter or a dash is rejected at definition time, usually after the rest of the import has already run. Typical input {"namespace": "custom", "key": "Care-Instructions"} returns {"ok": false, "problems": ["key: dashes and capitals are not allowed"], "suggested_key": "care_instructions"}. Use when designing metafields. Not for the CSV column that carries them — that is product_csv_check. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
bulk_price_changeApply one pricing rule across a list of prices and show the effect. PREMIUM (license). Percentage first, then the flat amount, then rounding — stated explicitly because the order changes the answer. Typical input {"prices": [19.99, 24.5], "change_pct": 10, "charm_ending": ".99"} returns {"rows": [{"was": 19.99, "now": 21.99}, {"was": 24.5, "now": 26.99}], "total_was": 44.49, "total_now": 48.98, "uplift_pct": 10.09}. Use when repricing a catalogue before export. Not for what a price nets you after Shopify's fees — that is payout_estimate. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "prices must contain at least one price"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
payout_estimateEstimate what actually lands in the bank after processing fees. PREMIUM (license). Typical input {"order_total": 84.5, "fee_pct": 2.9, "fee_fixed": 0.3, "orders": 120, "refund_rate_pct": 4} returns {"gross": 10140.0, "fees": 330.06, "refunds": 405.6, "net_payout": 9404.34, "effective_fee_pct": 3.26}. Use for cash-flow planning. Not as an authoritative fee schedule: rates depend on your plan, country and card mix, so pass your own. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.