News Featured

Trawl Is Now in Private Beta (Plus MCP Upgrades)

Trawl is now in private beta: limited seats, free plan, no credit card. Plus a sharper MCP server for AI agents, fairer billing, and reliability polish.

Pierre

• 5 min read
Share
Trawl banner: news grainy gradient with filet mesh

Give Your Agent a Web Tool That Doesn't Get Blocked

Your AI agent is only as smart as the pages it can actually read, and most of the web now answers a bot with a block screen or a CAPTCHA, not its content. Trawl is a hosted Model Context Protocol server that hands your agent a stealth-tier web-read tool: point it at almost any URL, get structured JSON back, with no browser infrastructure to run. Today we are opening it in private beta.

Your agent shouldn't have to lose a fight with a CAPTCHA to read a web page. Limited seats, free to start, no credit card.

What You'll Learn

What Trawl Gives Your Agent

You connect Trawl once, and your agent gets a web-read tool built for the sites that fight back, not just the easy ones:

  • Gets past anti-bot defenses: stealth-tier rendering handles the bot-detection and CAPTCHAs that stop ordinary scrapers at the door, so your agent reads the page instead of a block screen.
  • No infrastructure to run: no headless browsers, no proxy pool, no patching every time a site ships new defenses. Trawl runs all of it; your agent just calls a tool.
  • Self-healing extraction: when a site changes its layout, Trawl's AI repairs the extraction instead of returning empty fields, so scheduled jobs keep delivering.
  • Structured results: every run returns clean JSON your agent can act on, plus a screenshot and full run history.

Point your agent at a product page sitting behind anti-bot, ask for the fields you want, and you get structured data back. A scraper that returns data instead of excuses, that's the whole pitch.

Want this for your agent? Request a Trawl beta seat. The free plan needs no credit card.

Latest Update: In-App Docs and Reliability at Scale

Since the beta opened we shipped a larger release (June 2026) focused on two things people kept asking for: documentation you can actually use inside the product, and scraping that holds up when a lot of jobs fire at once.

This release touches the web app, the platform, billing, and security; the MCP server and CLI are unchanged this cycle.

  • 馃寪 Web app 路 In-app documentation: a new docs hub now lives inside the app, with role-based guides for three kinds of users, an API reference, copy-with-my-key snippets, and full-text search. The path from "what is this" to "first scrape running" no longer leaves the product.
  • 鈿欙笍 Platform 路 Reliability at scale: scheduled and async runs now go through a job queue with a global concurrency cap, so a burst of jobs landing at once no longer stampedes the browser layer. And when an account hits its limit you see it directly in the web app, a quota-pause badge and an exhaustion banner on the scraps list, plus cron-pause visibility, instead of jobs failing quietly. The reasoning behind building this on the database we already run, rather than a message broker, is its own story.
  • 馃挸 Billing 路 Fairer metering: premium-proxy bandwidth is now metered to what a run actually uses, and the free-tier copy reflects the one-shot trial honestly.
  • 馃敀 Security 路 Hardening: we closed a handful of server-side-request and tenant-isolation issues as part of routine hardening. Nothing you have to do, just the unglamorous work of keeping a multi-tenant scraper safe.

What's New in This Release

Most of this release went into the MCP server, the surface your agent actually talks to. If you are building agents, four changes earn their keep:

  • 馃攲 MCP 路 Markdown responses: ask for markdown and your agent reads a clean, ready-to-use answer instead of burning tokens parsing raw JSON.
  • 馃攲 MCP 路 Keyset-cursor pagination on list_scraps: listing stays fast and consistent no matter how many scraps you have, so an agent can walk the full set without timeouts.
  • 馃攲 MCP 路 Prefixed tool names: every tool now also registers as trawl_*, so it is unambiguous when your agent loads a dozen servers. The old names still work, nothing breaks.
  • 馃攲 MCP 路 Structured output via outputSchema and structuredContent: typed, predictable results your agent can rely on instead of guessing the shape.

Same endpoint: point your MCP client at api.trawl.me/api/mcp over Streamable HTTP.

Reliability and Polish

The rest of the release is the quiet work that makes the product feel solid:

  • 鈿欙笍 Platform 路 Correct screenshot formats: run screenshots are stored with the right image type, detected from the file itself, so previews always render.
  • 鈿欙笍 Platform 路 Steadier scheduling: a boot smoke-test gate and a cross-pod heartbeat catch cron problems before they reach you.
  • 馃寪 Web app 路 A clearer wizard: a brand-glyph catalog, a net-sweep loader, and a centered chat bubble make scrap setup easier to follow.
  • 馃寪 Web app 路 Redesigned settings: the scrap settings drawer moved to a master-detail layout, with several rounds of polish on top.
  • 馃寪 Web app 路 Better defaults: digest emails are now opt-in, and the chat keeps the previous run's screenshots so you can compare two runs at a glance.
  • 馃寪 Web app 路 Safer content: legal pages run through DOMPurify sanitization, and the running app version is visible in the footer.

How to Request Access

Trawl is in private beta, so seats are limited. The banner on trawl.me shows how many are left and a Request access link. Tell us what you are building, and we send invites as seats open.

Once you are in, the free plan starts you with 500 compute credits, no credit card, enough to run real scrapes and watch your agent work before you commit to anything.

Key Takeaways

  1. Trawl gives your agent a stealth-tier web-read tool that gets past anti-bot defenses, with no browser infrastructure to run.
  2. The June 2026 release adds an in-app docs hub and a job-queue-backed scraping engine that stays reliable under concurrency.
  3. Self-healing extraction keeps scheduled jobs delivering when sites change their layout.
  4. This release sharpens the MCP server: markdown answers, keyset pagination, trawl_* tool names, and structured output.
  5. Private beta is open: limited seats, free plan, 500 compute credits, no credit card. Request access at trawl.me.

If you want managed, stealth-tier web data for your agents without running browser infrastructure, Trawl can help. Request a seat and try it free.

FAQ

How do I get into the Trawl private beta?

Go to trawl.me and click Request access in the beta banner, which also shows how many seats are left. Tell us what you are building, and we send invites as seats open. Once you are in, the free plan starts you with 500 compute credits, no credit card.

Can Trawl scrape sites that block bots?

Yes, that is the point. Trawl uses stealth-tier rendering designed to get past the anti-bot defenses and CAPTCHAs that stop ordinary scrapers, with no setup on your side. It is not a guarantee for every site, but it handles cases that block most tools.

Does the Trawl beta cost anything?

No. The free plan starts you with 500 compute credits at signup, with no credit card. That is enough to run real scrapes and evaluate Trawl before choosing a paid plan.

What is the Trawl MCP server?

It is a hosted Model Context Protocol endpoint that lets an AI agent use Trawl as a set of tools: scrape a URL, schedule recurring scrapes, trigger runs, and read structured results. It speaks JSON-RPC 2.0 over Streamable HTTP at api.trawl.me/api/mcp.

Did the MCP tool names change? Will my agent break?

No breakage. Every tool now also registers under a trawl_ prefix so it is unambiguous in agents that load many servers. The original names still work, so existing integrations keep running unchanged.

What is keyset-cursor pagination on list_scraps?

Instead of paging by offset, list_scraps now returns a cursor that points to the next page. This keeps listing fast and consistent even when you have a large or growing number of scraps.

Which MCP clients work with Trawl?

Any JSON-RPC 2.0 client that supports Streamable HTTP, including Claude Desktop, Cursor, and n8n. Add the api.trawl.me/api/mcp endpoint with an Authorization bearer token and your agent gets the Trawl tools.

Is there a CLI or API as well?

Yes. The @trawlme/cli npm package lets you log in with trawl login, and the full tool and endpoint reference lives at api.trawl.me/api/docs.

Written by Pierre | June 2026