What is MCP for Shopify?
M
C
P
f
o
r
S
h
o
p
i
f
y
m
e
a
n
s
c
o
n
n
e
c
t
i
n
g
a
n
A
I
c
l
i
e
n
t
t
o
y
o
u
r
s
t
o
r
e
t
h
r
o
u
g
h
t
h
e
M
o
d
e
l
C
o
n
t
e
x
t
P
r
o
t
o
c
o
l
,
s
o
t
h
e
a
s
s
i
s
t
a
n
t
c
a
n
r
e
a
d
o
r
d
e
r
s
,
c
u
s
t
o
m
e
r
s
,
p
r
o
d
u
c
t
s
a
n
d
a
n
a
l
y
t
i
c
s
d
i
r
e
c
t
l
y
r
a
t
h
e
r
t
h
a
n
y
o
u
e
x
p
o
r
t
i
n
g
t
h
e
m
.
G
o
M
a
r
b
l
e
r
e
a
c
h
e
s
S
h
o
p
i
f
y
t
h
r
o
u
g
h
t
h
e
A
d
m
i
n
A
P
I
,
s
o
t
h
i
s
i
s
s
t
o
r
e
d
a
t
a
r
a
t
h
e
r
t
h
a
n
s
t
o
r
e
f
r
o
n
t
d
a
t
a
.
How to connect Shopify to GoMarble MCP
Connect Shopify once in GoMarble, then point any supported AI client at the MCP server.
- S
- i
- g
- n
- u
- p
- o
- n
- G
- o
- M
- a
- r
- b
- l
- e
- ,
- c
- o
- n
- n
- e
- c
- t
- y
- o
- u
- r
- S
- h
- o
- p
- i
- f
- y
- s
- t
- o
- r
- e
- u
- n
- d
- e
- r
- I
- n
- t
- e
- g
- r
- a
- t
- i
- o
- n
- s
- ,
- t
- h
- e
- n
- a
- d
- d
- t
- h
- e
- G
- o
- M
- a
- r
- b
- l
- e
- M
- C
- P
- s
- e
- r
- v
- e
- r
- a
- s
- a
- c
- u
- s
- t
- o
- m
- c
- o
- n
- n
- e
- c
- t
- o
- r
- i
- n
- y
- o
- u
- r
- A
- I
- c
- l
- i
- e
- n
- t
- .
- T
- h
- e
- s
- a
- m
- e
- c
- o
- n
- n
- e
- c
- t
- i
- o
- n
- s
- e
- r
- v
- e
- s
- e
- v
- e
- r
- y
- c
- l
- i
- e
- n
- t
- y
- o
- u
- a
- d
- d
- .
Connecting to Claude
The current steps, from the GoMarble MCP page:
- Open Settings, then Connectors.
- Choose Add custom connector.
- Enter https://apps.gomarble.ai/mcp-api/sse, then select Authorize.
- Choose the GoMarble workspace and accounts Claude can use.
Authorization uses GoMarble’s consent and workspace permissions, completed in the browser window your client opens.
Other supported clients
GoMarble MCP is a remote MCP server at https://apps.gomarble.ai/mcp-api/sse, currently supported in Claude, ChatGPT, Cursor, n8n, Hermes and OpenClaw, plus other clients that support compatible remote or local MCP servers. Setup differs slightly per client, so follow the canonical instructions rather than adapting the Claude steps.
View the complete GoMarble MCP setup guide →
What the free plan includes
- Up to $50,000 in cumulative ad spend
- One account per data source
- No edit actions — read and analysis only
What can you do with GoMarble MCP for Shopify?
Grouped by the job rather than by the tool that does it.
Analyze
- Query orders by whatever criteria you describe
- Run store analytics queries for revenue, AOV and order volume
- Read product and customer records
Investigate
- Look up any Shopify record by its id
- Check which products are actually selling against which are being advertised
- Compare store revenue against what the ad platforms claim
Act
- Not supported — Shopify is read-only on this connection
GoMarble MCP capabilities for Shopify
| Capability | What GoMarble MCP can do |
|---|---|
| Orders | Query orders by date, value, status or any criteria you can describe |
| Customers | Query customer records, including repeat behaviour |
| Products | Query the catalogue and see what is selling |
| Store analytics | Run analytics queries for revenue, AOV and order volume |
| Record lookup | Fetch the full detail of any record by its Shopify id |
| Execution | Not available — no write tools, so nothing in the store can be changed |
What data can GoMarble MCP access?
The data available for Shopify, grouped by type.
Store
Connected shops
Commerce
Orders · Customers · Products
Analytics
Store analytics queries
Lookup
Full record detail by id
GoMarble MCP workflows for Shopify
Jobs marketers actually want done, rather than features. Each one is a single natural-language request.
Reconcile store revenue with ad platforms
“How does Shopify revenue compare to what Meta claims this month?”
What GoMarble MCP does: Pulls store revenue and platform-attributed revenue from the same connection, so the gap is explainable rather than mysterious.
What you get:
Check what is actually selling
“Which products sold most last month, and are we advertising them?”
What GoMarble MCP does: Queries product sales and sets them against what the ad accounts are promoting.
What you get:
Find the AOV behind a ROAS change
“Did AOV move last month?”
What GoMarble MCP does: Runs a store analytics query for order value, which often explains a ROAS shift that looked like an ad problem.
What you get:
Look at repeat behaviour
“What share of last month's orders were repeat customers?”
What GoMarble MCP does: Queries customer records and order history to separate new from returning revenue.
What you get:
Check stock against spend
“Are we spending on products that are out of stock?”
What GoMarble MCP does: Reads the catalogue and compares against what the ad accounts are actively promoting.
What you get:
Investigate a revenue dip
“Why did store revenue fall last week?”
What GoMarble MCP does: Queries orders for both periods and splits the change into order volume versus average order value.
What you get:
Example GoMarble MCP prompts for Shopify
Things real marketers ask, grouped by intent. Paste any of them once connected.
Revenue
- “What was store revenue last month?”
- “How does this month compare to last?”
- “What is my average order value this quarter?”
- “Show me revenue by week for the last 90 days”
- “Which day of the week converts best?”
Products
- “Which products sold the most last month?”
- “What is in my catalogue?”
- “Which products have I never advertised?”
- “Show me products by revenue”
Customers
- “How many repeat customers did I have last month?”
- “What share of revenue comes from returning customers?”
- “Show me my highest-value customers”
Cross-channel
- “Compare Shopify revenue against Meta-attributed revenue”
- “Which ad channel drives the highest AOV?”
- “Does platform ROAS match store revenue this month?”
Why use GoMarble MCP for Shopify?
An API gives AI access to data. GoMarble MCP gives it the marketing context and workflows needed to work with that data.
GoMarble MCP for cross-platform marketing analysis
Marketers rarely decide anything from one platform. GoMarble MCP can give AI a view of the wider marketing system rather than forcing it to reason from one disconnected source at a time.
| Combination | What becomes answerable |
|---|---|
How does GoMarble MCP work?
| Step | What happens |
|---|---|
| 1 | You ask a question in natural language |
| 2 | The AI client works out what information it needs |
| 3 | GoMarble MCP retrieves the relevant marketing data and tools |
| 4 | GoMarble supplies the marketing context around it |
| 5 | The AI analyses the result |
| 6 | You get an answer, a recommendation, a report — or a proposed action |
Write access is plan-dependent. On the read-only plan you can connect a client and analyse supported accounts without making changes. Where write access is enabled, changes are proposed rather than applied directly — every write tool in the server is a propose call, and consequential actions route through the permissions and approval gates configured for your workspace.
Who is GoMarble MCP for?
Ecommerce operators
Check store performance and ad performance in the same question.
Performance marketers
Sanity-check platform-reported revenue against what the store actually took.
Agencies
Pull client store data alongside ad data for reporting without a second login.
GoMarble MCP vs traditional Shopify workflows
| Traditional workflow | With GoMarble MCP |
|---|---|
Frequently asked questions
What is MCP for Shopify?
Can it change anything in my store?
Is this the same as Shopify's Storefront MCP?
Why connect the store to an ad tool?
Which AI clients work with it?
What does the free plan allow?
Does it work with other ecommerce platforms?
Do I need a Shopify app or token?
Why GoMarble MCP?
The work you stop doing:
- S
- t
- o
- r
- e
- r
- e
- v
- e
- n
- u
- e
- a
- n
- d
- a
- d
- s
- p
- e
- n
- d
- a
- n
- s
- w
- e
- r
- a
- b
- l
- e
- i
- n
- o
- n
- e
- c
- o
- n
- v
- e
- r
- s
- a
- t
- i
- o
- n
- ,
- w
- h
- i
- c
- h
- i
- s
- w
- h
- e
- r
- e
- m
- o
- s
- t
- e
- c
- o
- m
- m
- e
- r
- c
- e
- r
- e
- p
- o
- r
- t
- i
- n
- g
- d
- i
- s
- p
- u
- t
- e
- s
- a
- c
- t
- u
- a
- l
- l
- y
- g
- e
- t
- s
- e
- t
- t
- l
- e
- d
- .
Connect your marketing stack once. Give AI the context it needs. Ask in plain English, and let it analyse, explain, recommend and — where enabled — propose the change.
Your Shopify data is already there. Now give AI access to it.
Connect GoMarble MCP to your marketing stack and start analysing Shopify from the AI tool you already use.