Run Your Shopify SEO from Gemini CLI
Gemini CLI is Google's command-line AI agent, and it can call external tools through the Model Context Protocol. Connected to StoreSEO, it reads your store's SEO scores, previews optimized meta and applies the changes you approve from the terminal you already work in.
- One command: gemini mcp add
- OAuth discovered automatically, no client ID to paste
- Per-server tool filters and confirmations built in
Last updated: October 2026
-
You: Find my three lowest-scoring products and show me better meta for each.
- storeseo_start read-only
- storeseo_list_resources read-only
- storeseo_preview_resource_optimization preview
-
Gemini CLI: StoreSEO drafted new meta, tags and FAQs for all three. Previews used AI credit and nothing is saved yet. The new URL handles change, so old links will redirect. Apply the meta and FAQs and keep the current handles?
-
You: Yes, apply those and keep the handles.
- storeseo_apply_resource_optimization needs approval
-
Gemini CLI: Applied without the handle changes. All three re-scored. Want me to look at the images on those products next?
StoreSEO is the AI SEO Agent for Shopify merchants — a Shopify app that optimizes your store for Google and gets it cited by ChatGPT, Gemini, Claude and Perplexity.
5.0/5 from 750+ Shopify reviews
How do I connect Gemini CLI to StoreSEO?
- 1
Add StoreSEO to Gemini CLI
Run this in any terminal. The user scope writes the server to ~/.gemini/settings.json so every project sees it. Without --scope user the command writes to the current project's .gemini/settings.json.
Terminalgemini mcp add --scope user --transport http storeseo https://mcp.storeseo.com/mcp
- 2
Sign in to your store
Start gemini. The first time it calls StoreSEO it opens your browser: pick your Shopify store and approve access. If the window does not open, type /mcp auth storeseo inside Gemini CLI. Then gemini mcp list should show storeseo as connected.
Prompt/mcp auth storeseo
- 3
Or edit settings.json Optional
Add this to ~/.gemini/settings.json for every project, or to .gemini/settings.json in one project. It is the entry gemini mcp add writes: url plus type set to http. The docs page still shows the older httpUrl key for streamable HTTP.
JSON{ "mcpServers": { "storeseo": { "url": "https://mcp.storeseo.com/mcp", "type": "http" } } } - 4
Or connect with an access token Optional
On a headless machine the browser sign-in cannot run. Generate a token in StoreSEO under Settings, AI Toolkit and pass it as a header. Keep the token out of version control.
Terminalgemini mcp add --scope user --transport http \ --header "Authorization: Bearer YOUR_TOKEN" \ storeseo https://mcp.storeseo.com/mcp
Sign-in
Gemini CLI finds the StoreSEO sign-in on its own: the first time it calls the server it opens your browser, you pick your Shopify store and approve, and it stores the tokens. On a machine with no browser, add a personal access token from StoreSEO under Settings, AI Toolkit as a header.
Check it worked
Use StoreSEO to show me my store's SEO score breakdown.
What is Gemini CLI?
Gemini CLI is Google's open-source command-line AI agent. You run it in a terminal, it reads the folder you start it in, and it works through tasks by calling built-in tools and tools from MCP servers.
MCP servers live under mcpServers in settings.json, either ~/.gemini/settings.json for every project or .gemini/settings.json for one. You can add one with gemini mcp add, choosing the stdio, sse or http transport and a user or project scope. For remote servers that need a sign-in, Gemini CLI detects the 401 response, discovers the OAuth endpoints, registers itself when the server allows it and opens your browser.
Each server can set trust, which skips tool confirmations and is off by default, and includeTools or excludeTools lists to control exactly which of its tools the model sees. MCP tools appear to the model as mcp_<server>_<tool>.
Why use Gemini CLI with StoreSEO?
Sign-in with nothing to paste
Gemini CLI discovers StoreSEO's OAuth endpoints and registers itself, so there is no client ID or secret to copy. You approve your store once in the browser.
Trim the tool list per server
Use excludeTools or includeTools to hide StoreSEO tools you never use, so the model sees a shorter list and has fewer ways to pick the wrong one.
Confirmations by default
Gemini CLI asks before running an MCP tool unless you trust the server, so a StoreSEO write has to get past Gemini CLI's prompt as well as StoreSEO's own confirmation.
Good to know
- Google's site says Gemini CLI was replaced by Antigravity CLI on June 18th, 2026 for unpaid tier and Google One users. If that is you, check which command-line agent your account can still use before you set this up.
- gemini mcp add defaults to project scope, so a server added without --scope user is only available in that project.
- Do not set --trust or trust: true on the storeseo server. Trust skips every tool confirmation, and then the confirmation StoreSEO asks for in chat is the only check.
- The browser sign-in needs a browser on the same machine. In a headless session or over SSH without a browser, use the access token header instead.
What can you ask Gemini CLI to do in StoreSEO?
Use StoreSEO to list every product scoring under 50 and preview new meta for the first five.
Which product images have no alt text? Show me the ten heaviest first.
Is my llms.txt up to date? If not, tell me what generating a new one will change before you run it.
Show me Search Console queries from the last 28 days where we rank between 8 and 20.
Which schema types are enabled for my store, and what would turning on Product schema add?
Gemini CLI guides by job
Each guide covers one StoreSEO job end to end in Gemini CLI: setup, prompts, an example session, the rules and the limits.
Which way should you connect?
MCP server with OAuth
- Best for
- Claude, ChatGPT and any client that supports remote MCP sign-in
- Sign-in
- Pick your store in Shopify and approve once
- What you get
- All 44 tools, scoped to the store you approved
MCP server with an access token
- Best for
- Terminal agents and editors, or any client without OAuth
- Sign-in
- Generate a named token in Settings, AI Toolkit and send it as a Bearer header
- What you get
- The same 44 tools; revoke the token in the app to cut access
Shopify Sidekick
- Best for
- Merchants who stay inside Shopify admin
- Sign-in
- Nothing to add: StoreSEO is installed in your store
- What you get
- SEO answers and deep links to the fix page, not the MCP tools
What runs without asking. Reads such as SEO scores, store listings, settings and Google reports run straight away. Generating a preview spends AI credit but writes nothing, and StoreSEO tells the agent to say what a generation will cost before it runs one. Applying content, optimizing images, changing settings, publishing llms.txt or agents.md, writing a product description and deleting anything wait for your yes in the conversation. That yes is an instruction the agent follows, not a lock on the server, so your client's own tool-approval setting is the hard stop.
Questions
How do I connect Gemini CLI to StoreSEO?
Run gemini mcp add --scope user --transport http storeseo https://mcp.storeseo.com/mcp, then start gemini. The first call to StoreSEO opens your browser, where you pick your Shopify store and approve access. You can also type /mcp auth storeseo to start the sign-in yourself.
Do I need a StoreSEO API key for Gemini CLI?
No. Gemini CLI signs in with OAuth and stores the tokens it receives. A personal access token from StoreSEO under Settings, AI Toolkit is the alternative for machines without a browser, added with the --header option.
Where does Gemini CLI store the StoreSEO server?
With --scope user it is written to ~/.gemini/settings.json and is available in every project. Without that option it is written to the .gemini/settings.json file of the current project only.
Will Gemini CLI change my store without asking?
StoreSEO tells the agent to preview first and wait for your yes before it applies content, optimizes images, publishes a file or deletes anything, and that yes is an instruction the agent follows, not a lock on the server. Gemini CLI also asks for confirmation before an MCP tool runs unless you mark the server as trusted, and that setting is the hard stop. Reads such as scores and reports run straight away.
Which StoreSEO plan does Gemini CLI need?
Any active StoreSEO plan, including the free plan, can use the MCP server. Rank tracking is a Pro feature, Google reports need a paid plan with Google connected, and generated content spends AI Content Optimizer credit. See the pricing table for current plans.
Can I hide some StoreSEO tools from Gemini CLI?
Yes. Add --exclude-tools to the gemini mcp add command, or an excludeTools list to the storeseo entry in settings.json, with the names of the tools you do not want the model to see. An includeTools list does the opposite and allows only the tools you name.
How do I disconnect Gemini CLI from my store?
Run gemini mcp remove storeseo, adding --scope user if you added it with that scope. Then revoke the connection or the access token in StoreSEO under Settings, AI Toolkit, where every connected app is listed.