How to Connect StoreSEO MCP to 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.

This guide connects Gemini CLI to the StoreSEO MCP server at https://mcp.storeseo.com/mcp. Once connected, Gemini CLI can read your Shopify store’s SEO scores and settings and, when you agree, apply optimized meta, alt text, schema and other SEO changes. For what to ask once you are set up, see StoreSEO for Gemini CLI.

Before You Start

Server URL: 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.
Plan: The MCP server works on any active StoreSEO plan, including the free plan. A store with no active plan gets a message with a link to choose one in the app.
Access token (if you need one): create it in the StoreSEO app under Settings, AI Toolkit. Treat it like a password.

Connect StoreSEO to Gemini CLI

Step 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.

gemini mcp add --scope user --transport http storeseo https://mcp.storeseo.com/mcp

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.

/mcp auth storeseo

Other Ways to Connect

Option: Edit settings.json

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.

{
  "mcpServers": {
    "storeseo": {
      "url": "https://mcp.storeseo.com/mcp",
      "type": "http"
    }
  }
}

Option: Connect with an access token

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.

gemini mcp add --scope user --transport http \
  --header "Authorization: Bearer YOUR_TOKEN" \
  storeseo https://mcp.storeseo.com/mcp

Check the Connection

Start a new session and send this prompt. Gemini CLI should call StoreSEO and answer with your store’s real SEO score.

Use StoreSEO to show me my store's SEO score breakdown.

What to Ask Gemini CLI

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?

How Approvals Work

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.

Things to Know About Gemini CLI

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.

Disconnect

Remove the StoreSEO server in Gemini CLI, then revoke the connection or the access token in the StoreSEO app under Settings, AI Toolkit, where every connected client is listed.