Optimize meta tags and content with NanoClaw
Optimizing meta tags with NanoClaw means asking your self-hosted agent, in a chat message, to have StoreSEO draft a meta title, description, tags and URL handle for one Shopify resource and to save only the parts you answer yes to.
Last updated: October 2026
Set up NanoClaw for StoreSEO
Skip this if NanoClaw is already connected. The full guide, with the alternatives, is on the NanoClaw page.
- 1
Create a StoreSEO access token
In the StoreSEO app open Settings, AI Toolkit and generate a personal access token. Keep it out of chat messages and out of Git.
new message to NanoClawSettings → AI Toolkit → create a token
- 2
Add StoreSEO to your agent's container
Run this on the machine that hosts NanoClaw, using your agent group's ID from ncl groups list. The header goes in as a JSON object. NanoClaw may ask an admin to approve the change.
terminalncl groups config add-mcp-server --id <group-id> --name storeseo \ --url https://mcp.storeseo.com/mcp \ --headers '{"Authorization":"Bearer YOUR_TOKEN"}' - 3
Restart the agent's container
The new server takes effect after a restart. Then message your agent with its trigger word, @Andy by default, and ask for your store's SEO score.
terminalncl groups restart --id <group-id>
Step-by-step guide in the docs: How to connect StoreSEO MCP to NanoClaw
How does this work in NanoClaw?
The whole exchange happens in one chat thread. You message the agent with its trigger word and name a single product, for instance @Andy improve the meta on my Soy Candle. The agent calls storeseo_get_resource_seo to read the current title and description, then storeseo_preview_resource_optimization. StoreSEO writes the draft on its own servers, so the words come from StoreSEO and not from the model behind NanoClaw. The response carries a draft id and a projected score change, and the agent pastes the old and new text into the chat so you can compare them on your phone.
Reply in plain words. If you say apply the title and description but skip the handle, the agent passes only those fields to storeseo_apply_resource_optimization. A changed URL handle creates a redirect from the old address, which is why the agent should show both addresses before that call. The preview spends AI Content Optimizer credit even if you decline, so name one product at a time. Your yes in the thread is an instruction the agent follows. Whether NanoClaw itself pauses before the tool runs depends on your fork and your admin approval settings, so the chat confirmation may be the only check you have.
Do the previews in the conversation and keep them out of scheduled tasks. A task that previews on a cron schedule would spend credit every run and has no one to approve the result. A better pattern is a report only task that lists the lowest scoring products each week, followed by a chat where you pick one and walk through its meta.
-
You: @Andy use StoreSEO to improve the meta on my Soy Candle product.
- storeseo_start read-only
- storeseo_get_resource_seo read-only
-
NanoClaw: The meta description is empty. A preview spends AI Content Optimizer credit and saves nothing. Should I generate one?
-
You: Yes, go ahead.
- storeseo_preview_resource_optimization preview
-
NanoClaw: Illustrative draft: a new title and description, score projected from 31 to 78. Apply the title and description only, and leave the handle alone?
-
You: Yes, apply those two.
- storeseo_apply_resource_optimization needs approval
What to ask NanoClaw
Tap a prompt to copy it, then paste it into NanoClaw.
What StoreSEO does: meta tags and on-page content
StoreSEO generates the content server-side: meta title and description, tags, a keyword-led URL handle, FAQs and an AI snippet. The agent shows you the draft and the projected score change before anything is saved, then applies all of it or only the parts you approve.
Requires: Generating a preview spends AI Content Optimizer credit; applying a preview is free.
- 1
Read the current state
The agent reads the resource's SEO record so it knows which fields exist, which fail and what the preview will add.
- 2
Generate a preview
StoreSEO writes the meta title, description, tags, URL handle, FAQs and AI snippet and projects the new SEO score, plus the GEO score for products. Nothing is saved yet. Preview spends credit whether or not you apply it.
- 3
Show you the draft
The agent presents the generated text and the score change. When the handle changes it shows the old and new URL and tells you a redirect will be created.
- 4
Apply what you approve
After your yes it applies everything, or only the parts you chose, for example the meta but not the FAQs. Skipped fields stay available from the same draft for an hour.
- 5
Report the new score
The apply call returns the recomputed score and the remaining checklist, so the agent tells you what changed and offers the next most useful fix.
Meta tags and on-page content reference
| Generated fields | Meta title, meta description, tags, URL handle, FAQs, AI snippet |
|---|---|
| Resource types | Products, collections, pages and articles (collections have no meta tags or tags axis in auto settings) |
| Who writes the copy | StoreSEO, server-side. The agent never authors meta, FAQs or handles itself |
| Cost | Preview spends AI Content Optimizer credit; apply is free; a new preview spends again |
| Draft lifetime | One hour after the preview |
| URL handle | Applying a new handle changes the live URL and creates a redirect from the old one; a handle already in use is dropped automatically |
| Partial apply | Apply a subset of axes, or skip individual fields such as the handle |
| Auto optimization | Optional settings that generate content for newly synced resources; only future syncs, nothing is backfilled |
| Auto settings plan | Configurable on any plan; switching an auto toggle on needs a paid plan and no active trial |
Rules NanoClaw follows
- The agent previews first and applies only after you confirm the previewed content.
- When a handle changes, you see the old URL and the new URL before the apply call, because applying creates a redirect.
- A request like optimize my worst five products authorizes the previews; the agent should remind you that previews spend credit even if you do not apply them.
- Turning on auto optimization spends credit on every future sync, so the agent proposes the exact sections and waits for your yes.
- Product title, focus keyword and description body are not written by this job; the description has its own tool in the AI search job.
In NanoClaw
On a chat app a yes can be misread. If you send a quick thumbs up or a reply that lands on a different message in a busy Slack or Discord channel, the agent may take it as consent for the wrong draft. Reply in a full sentence that names the product and the fields, such as yes, apply the Soy Candle title and description. If your fork has no tool approval, that sentence is the only brake before the write.
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
Does the model behind NanoClaw write my meta text?
No. StoreSEO generates the meta title, description, tags, handle, FAQs and AI snippet on its own servers. NanoClaw's agent fetches the draft, shows it in the chat and passes along only the fields you approve.
How do I make NanoClaw ask before it saves meta?
StoreSEO tells the agent to preview first and wait for your yes. That is an instruction, not a lock, so the hard stop is whatever approval behavior you set in your own fork. Test it once with a harmless product before trusting it.
Does previewing an optimization change my product?
No. A preview generates the content and projects the score without saving anything. It does spend AI Content Optimizer credit, and applying the draft afterwards is free.
What happens to the old URL when the handle changes?
Applying a new URL handle updates the live URL and StoreSEO creates a redirect from the old one, so existing links keep working. The agent should show you both URLs before it applies the change.
Can I apply only part of a preview?
Yes. The apply step takes the axes you approved, and individual content fields such as the URL handle can be skipped. Skipped parts stay available from the same draft for one hour.
Does auto optimization fix my existing products?
No. Auto optimization only acts on resources synced or updated after you turn it on. Existing products are fixed with the preview and apply steps in this job.
Will StoreSEO change my product title?
No. This job writes the SEO meta title, not the storefront product title. The product title is edited in Shopify admin.
Keep going
Meta tags and on-page content with other agents
More NanoClaw guides