browserless_smart_scrape
Pack: browserless · Endpoint: https://gateway.pipeworx.io/browserless/mcp
AI-assisted extraction: tries a plain HTTP fetch first and falls back to a full headless browser, returning content in the requested formats (html, markdown, links, screenshot, pdf). Best when you just want clean page content and do not know the right selectors. Example: browserless_smart_scrape({ url: “https://example.com”, formats: [“markdown”, “links”], _apiKey: “your-token” })
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
url | string | yes | The page URL to extract |
formats | array | no | Which formats to return: any of “html”, “markdown”, “links”, “screenshot”, “pdf” (default [“html”]). “content” (raw HTML/parsed JSON) is always returned. |
items | string | no | |
proxy | string | no | Proxy pool: “residential” (default) or “datacenter” |
_apiKey | string | yes | Browserless API token (sign up at https://www.browserless.io/signup) |
_host | string | no | Optional region host override |
Example call
curl -X POST https://gateway.pipeworx.io/browserless/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"browserless_smart_scrape","arguments":{}}}'Connect
Add this to your MCP client config, or use one-click install buttons:
{
"mcpServers": {
"browserless": {
"url": "https://gateway.pipeworx.io/browserless/mcp"
}
}
}See Getting Started for client-specific install steps.