Optimize images and alt text with GitHub Copilot
Optimizing Shopify images with GitHub Copilot means using Agent mode in VS Code to list your heaviest and unlabelled images through StoreSEO and then compress them and write alt text and file names one image per call, with the theme workspace open alongside.
Last updated: October 2026
Set up GitHub Copilot for StoreSEO
Skip this if GitHub Copilot is already connected. The full guide, with the alternatives, is on the GitHub Copilot page.
- 1
Add StoreSEO to .vscode/mcp.json
Create or open .vscode/mcp.json in your workspace and paste this. VS Code uses a top-level servers key, not mcpServers, and a remote server needs type http.
JSON{ "servers": { "storeseo": { "type": "http", "url": "https://mcp.storeseo.com/mcp" } } } - 2
Start the server and sign in
Run MCP: List Servers from the Command Palette, pick storeseo and start it. If it asks you to sign in, pick your Shopify store in the browser and approve access. Then open Copilot Chat in Agent mode, check the tools icon lists StoreSEO and ask this.
PromptUse StoreSEO to show me my store's SEO score breakdown.
How does this work in GitHub Copilot?
You open the theme workspace in VS Code, switch Copilot Chat to Agent mode and ask it to list product images with no alt text and the heaviest unoptimized files. Copilot calls storeseo_start and storeseo_list_images, which are reads, and the tool calls show in the chat. The listing gives each image's compression, alt text and file name status, and since the workspace is open Copilot can search the theme for any file name before you decide to rename it, which is useful because a rename changes the image's storefront URL.
VS Code puts a confirmation in front of tool calls, and you choose how broadly to allow them. For this job keep storeseo_optimize_image and storeseo_restore_image on the confirmation prompt: it is the hard stop, and StoreSEO also tells the agent to name the Image Optimizer quota or AI credit a run will spend and wait for your yes. Each call handles one image and returns a report for compression, file name and alt text separately, so Copilot can say which part applied and which was refused rather than reporting one result for the batch.
If a result is wrong, ask Copilot to restore it with storeseo_restore_image for the axes you name, then re-list the image to confirm. Because the server entry lives in .vscode/mcp.json or your user configuration, check MCP: List Servers if the image tools do not appear in the chat's tools list.
-
You: List my images with no alt text and check whether the workspace uses any of them by file name.
- storeseo_start read-only
- storeseo_list_images read-only
-
GitHub Copilot: There are 24 images with no alt text. I searched the workspace: canvas-tote-main.jpg is used in templates/product.json, so I would not rename it. Shall I write alt text and compress the Canvas Tote images, one call each?
-
You: Yes, alt text and compression, no renames.
- storeseo_optimize_image needs approval
-
GitHub Copilot: First Canvas Tote image is compressed and has alt text. VS Code will ask you to allow the next call.
What to ask GitHub Copilot
In Agent mode, use StoreSEO to list my images with no alt text and the five heaviest unoptimized files. Change nothing.
Search this workspace for the file names of the Canvas Tote images, then compress them and write alt text, keeping the file names as they are.
Restore the last image you optimized, all three parts, and re-list it so I can see the status.
- Find my ten heaviest unoptimized product images and compress them. Tell me the quota it will use first.
- Which product images have no alt text at all? Write alt text for the ones on my best seller.
- Optimize every image on the product Canvas Tote: compression, alt text and file name.
- Restore the original alt text on the last image you changed.
- Give my collection images descriptive file names, and warn me which URLs will change.
What StoreSEO does: image seo and alt text
StoreSEO tracks three things per image: file-size compression, alt text and file name. The agent finds the heaviest or unlabelled images, optimizes them one call per image, and can restore any of the three if you do not like the result.
Requires: Compression needs the Image Optimizer add-on and counts against its monthly quota; alt text and file names spend AI Content Optimizer credit.
- 1
Find the images
The agent lists product, collection or article images, heaviest unoptimized first by default. It can filter to images with no alt text, or scope the list to one product by title.
- 2
Check what it found
A title search can also match image file names from other resources, so the agent checks each row belongs to the product you meant.
- 3
Agree the scope and cost
Compression uses image quota and alt text and file names use AI credit, so the agent confirms before working through many images.
- 4
Optimize one image per call
Each call takes the axes you want: compression, alt text, file name or all three. The axes always run compression, then file name, then alt text, and the response reports each one separately.
- 5
Report or restore
The agent reports what applied, what was already done and what was refused. If a result is wrong, the restore tool brings back the original file, alt text or name.
Image SEO and alt text reference
| Axes per image | Compression, alt text, file name |
|---|---|
| Image sources | Products, collections and articles (pages have no images) |
| Batching | One image per call; never two calls on the same image at once |
| Compression | Image Optimizer add-on and its monthly quota; an already compressed image is reported as already applied |
| Alt text and file name | AI Content Optimizer credit; both together are billed as one generation |
| File name change | Renames the file on Shopify and changes the image's storefront URL |
| Collection and article renames | Re-upload the image, so the call can take a couple of minutes |
| Restore | Reverts compression, alt text or file name per axis |
| Score impact | Alt text and file names count on products, collections and articles; compression counts on products |
Rules GitHub Copilot follows
- The agent confirms the number of images and the kind of spend before a bulk run.
- One image per call, all wanted axes together; never parallel calls on the same image.
- A renamed image has a new URL, so the agent tells you, because anything that hard-coded the old URL keeps serving the old file.
- If a response is lost, the agent re-lists the image instead of retrying, because a retry regenerates and spends again.
- A refused axis, for example compression without the add-on, is reported as such while the other axes still apply.
In GitHub Copilot
VS Code reads servers from the servers key in .vscode/mcp.json, so a StoreSEO entry copied from a Cursor or Claude snippet that uses mcpServers will not load and the image tools never show up in Agent mode. With one image per call, a long run also means many confirmation prompts. Resist allowing the optimize and restore tools for the whole session to save clicks, since that prompt is the hard stop in front of compression quota, AI credit and URL-changing renames.
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
Why are the StoreSEO image tools missing in Copilot Agent mode?
Check that the server entry uses the servers key in .vscode/mcp.json with type http, that MCP: List Servers shows storeseo running, and that the tools icon in Copilot Chat lists it. On Copilot Business and Enterprise an admin must also enable the MCP servers in Copilot policy.
Can Copilot check my theme before it renames an image?
Yes. In Agent mode it can search the open workspace for the current file name, so you learn whether a Liquid file or JSON template hard-codes it before you approve a storeseo_optimize_image call that includes the file name axis.
Can the agent compress images without the Image Optimizer add-on?
No. Compression needs the Image Optimizer add-on and counts against its monthly quota. Alt text and file names work without it and spend AI Content Optimizer credit instead.
Can I undo an image optimization?
Yes. The restore tool reverts compression, alt text or file name for one image, per axis. Restoring compression brings back the original file.
Why did my image URL change?
Giving an image a new file name renames the file on Shopify and re-points its storefront URL. Pages that use the image through Shopify keep working, but anything that hard-coded the old URL keeps the old file.
Can I write my own file name or alt text through the agent?
No. StoreSEO writes the alt text and file name from the resource's own context. You can steer the language, and you can always edit alt text yourself in Shopify admin.
Keep going
Image SEO and alt text with other agents
More GitHub Copilot guides