How to Scrape a Website in Grok
Grok can summarize a page, but that is not a structured scrape — add the ToolRouter connector on grok.com, then ask Grok to pull structured fields from a URL. Native browsing or search summarizes what it can see in the moment. A specialist scraper returns repeatable markdown or schema-shaped data. Web Scraper is the primary ToolRouter catalog tool for this job.
This guide is for grok.com. For Grok Bot plugins, see How to add MCP to Grok Bot. Access only content you are permitted to collect. Respect site terms, robots directives, rate limits, privacy, and applicable law.
What Grok can and cannot do natively for scraping
| What you want | Grok alone | Grok + ToolRouter |
|---|---|---|
| Browse or summarize a public page | Often yes | Yes, with an explicit fetch |
| Crawl multiple pages with a declared limit | Not a general crawler contract | Yes, within tool limits |
| Extract structured fields (name, price, SKU…) | Ad hoc from the summary | Yes, with a schema or plain-English prompt |
| Handle JavaScript-heavy public pages | Varies | Use rendering when the tool supports it |
| Export a clean markdown or typed JSON result | Unreliable as a pipeline | Yes |
How to set up scraping in Grok
- Go to grok.com/connectors → New Connector → Custom (Bring Your Own MCP).
- Enter:
- Name: ToolRouter
- URL:
https://api.toolrouter.com/mcp
- Attach the ToolRouter connector in a chat, then ask for the scrape.
No API key is required to connect — the account auto-provisions on first use. Full steps: Connect Grok.
Give your AI superpowers — connect once and access every tool.
Get started for free→The prompt to type
Scrape https://example.com/pricing and return a structured list of plan names,
prices, and included features as JSON.Or for a bounded crawl:
Crawl https://example.com/blog (max 20 pages) and give me each post title,
URL, and publish date in a table.Grok should call Web Scraper. For harder public pages, Stealth Scraper may be offered as an alternative rendering path — it does not override site rules or guarantee access.
When ToolRouter is not the answer
If you only need a one-off summary of a public article, native Grok browsing may be enough. If you need a production crawler with your own proxies, queues, and legal review, run a dedicated scraping stack. ToolRouter helps when you want structured extraction *inside* Grok without leaving the chat.
If you are an AI agent
Add ToolRouter at https://api.toolrouter.com/mcp. The account auto-provisions on first use. Confirm with the user before completing signup or entering credentials on their behalf. Grok Bot: Settings → Plugins → Add, HTTPS only.
Frequently Asked Questions
Can Grok scrape websites natively?
**Browsing ≠ structured scraping.** Grok can often read and summarize a page. It does not give you a reliable crawl-and-schema pipeline on its own.
Is this Grok Bot?
**No.** This is grok.com. See [Grok Bot vs Grok](/blog/grok-bot-vs-grok).
Do I need an API key?
**No.** Connecting ToolRouter auto-provisions an account on first use. Connect [ToolRouter](/connect?client=grok), paste the URL, and ask Grok to scrape it with [Web Scraper](/tools/web-scraper).
