browser-runlisted

# Browser Run (Claude Code) A real headless browser (Cloudflare Browser Run, headless Chrome) for public web pages that `WebFetch` can't read or that you need to *interact* with. There are **two surfaces**, and picking the cheaper one is the whole point of this skill — a real browser session is the most expensive way to touch a page. | Surface | Tools | Cost | Use it for | |---|---|---|---| | **Markdown / read** (one-shot) | `browser_markdown`, `browser_content`, `browser_scrape` (the `browser-run` MCP server) | Cheap — one request, no live session | **Reading** a page: article/doc content, verifying rendered text/structure, pulling specific elements. The default when you just need to *see what the page says*. | | **Interactive** | `mcp__chrome-devtools__*` (`navigate_page`, `take_snapshot`, `take_screenshot`, `click`, `fill`, `evaluate_script`, `resize_page`/`emulate`) | Expensive — holds a remote Chrome/CDP session | **Driving** a page: multi-step flows, clicking/typing, screenshots, viewport testing, e2e. | Both are Pro (advanced) only, and only when a Cloudflare API token with the **Browser Rendering – Edit** scope is configured. If you see neither the `browser_*` tools nor `mcp__chrome-devtools__*`, Browser Run is not enabled — fall back to `WebFetch` only. ## Decision order (cheapest that does the job) 1. **Static / normal page** → `WebFetch`, or `ctx_fetch_and_index` (context-mode) when the page is large or you only want specific facts (keeps the bytes out of your