Turn any web page into structured JSON, on a schedule, with alerts when it changes. That is Trawl. You describe what to watch and what to extract; Trawl runs a real headless browser (proxies, login, anti-bot handled for you), stores every run, and pushes the result to your dashboard, CLI, webhook, or AI agent.
What you can do in the next 5 minutes
- Watch a page and get JSON — point Trawl at a URL, describe the fields in plain English, get back structured data. → Quickstart
- Call it from your code — one
POSTwith an API key triggers a run and returns the payload. → Quickstart ends in a copy-pastecurl. - Drive it from Claude — connect the MCP server and let an agent create, run, and read scraps for you. → Using Trawl with Claude
Pick your path
| You are a… | Start here | Then |
|---|---|---|
| Developer — want REST/JSON | Quickstart → API keys | Webhooks |
| AI agent / Claude user | Using Trawl with Claude → MCP Server | Skills |
| No-code / web app | Quickstart → web wizard | Notifications |
Ways to consume Trawl
- Web app — create and inspect scraps, read results, manage keys and webhooks at trawl.me.
- REST API — trigger a run and read results over plain HTTP:
POST /api/scraps/worker/:id,GET /api/scraps,GET /api/scraps/:id,GET /api/historys. See Quickstart and API keys. - CLI —
trawl login, list and run scraps from the terminal. See@trawlme/clion npm. - MCP server — plug Claude Desktop, Cursor, or any MCP client into
https://api.trawl.me/api/mcpto discover and call Trawl tools directly. - Webhooks — receive push notifications on
scrap.success/scrap.failureagainst your own HTTPS endpoint.
Guide map
Get started
- Welcome — you are here
- Quickstart — first JSON result in minutes
Build your scrap
- Scraping basics
- Advanced scraping — proxies, login flows, validation
- Parameters
- Account & sessions
- Security
Run & monitor
Integrate
Use with Claude
- CLI
- Skills
- MCP Server
- Using Trawl with Claude — the agent-first end-to-end tutorial
Next step → Quickstart