Everything people ask,
answered properly

It turns web pages into spreadsheets. You install a Chrome extension, open the side panel next to any page, click one example of the thing you want, and Fyre works out the repeating pattern and pulls every match into a table. From there you filter it, dedupe it, and export CSV, Excel, JSON, or push it to a Google Sheet.

No. The whole flow is clicking on the page and adjusting columns. If you do write code, CSS selectors and regular expressions are available wherever a column is defined — but they are an escape hatch, not the main path.

Chrome, Edge, Brave, Arc, Opera and anything else built on Chromium 111 or newer. It uses the side panel API, so a genuinely old Chrome build will not run it. Safari and Firefox are not supported.

Yes. One payment of $15 unlocks every extractor, every export format, the AI agent connection and future updates. There is no monthly plan, no per-seat pricing, no row quota and no upsell waiting three screens in.

It means the licence does not expire and updates are included for as long as the product exists. It does not mean we can promise a product will exist forever — nobody can honestly promise that. What we can promise is that the extension keeps working locally on the machines you have activated, licence server or not.

Three activations per licence, and you can move an activation between machines from the account page. If you need more for a team, buy a licence per person — at $15 that is usually simpler than any seat-management scheme we could build.

Install it and use it. The free tier gives you every tool with a cap of 200 rows per extraction, which is enough to prove it works on the pages you care about. Paying lifts the cap and unlocks scheduled cloud runs.

Into your own browser. Rows are written to IndexedDB inside your Chrome profile, and they stay there until you export or delete them. Local extraction involves no upload of page content or results to us. Scheduled cloud runs are the exception — those execute on our infrastructure by definition, and the page explains exactly what is stored and for how long.

No. The extension does not report page URLs, page content or extracted rows. Licence validation sends a licence key and a machine identifier, nothing else, and you can read the network calls yourself in the DevTools panel.

It reads the page you already have open using the same session your browser already has. It never captures passwords, never touches other tabs unless you point it at them, and never sends cookies anywhere. Practically, treat exported data the way you would treat a screenshot of the same page.

Fyre exposes an MCP server. You add it to Claude Desktop, Claude Code, Cursor or any other MCP client with a short config block, restart the client, and the agent gains a set of scraping tools. Asking it to 'get every product on this category page as a table' is then a normal request.

That is exactly the problem it is built around. Results live in a table on Fyre's side; the agent gets a schema, a row count and a handle. It then filters, aggregates or samples that table and pulls in only the rows it needs. A 120,000-row run can cost a few hundred tokens in conversation.

Anything that speaks MCP. Claude Desktop and Claude Code are what we test against most, then Cursor and Windsurf. Clients that only support HTTP transports work through the hosted endpoint instead of the local one.

Yes, through cloud runs. Save a recipe in the extension, promote it to a scheduled run, choose an interval from every ten minutes to once a month, and pick a destination — a Google Sheet or your own webhook. Your laptop does not need to be open.

Nothing metered exists on the local side, so there is nothing to run up. Cloud runs have a hard page cap per run and a monthly cap per account, both of which you set, and a run stops at the cap rather than asking for more.

The recipe will start returning empty columns, and Fyre tells you that instead of writing blank rows quietly. Re-pointing a column takes one click on the new element. For scheduled runs you can set an alert threshold so an empty result emails you rather than overwriting yesterday's good data.

It depends on what you collect, where you are, and what you do with it — which is not a dodge, it is genuinely the answer. Publicly visible information is treated very differently from personal data, and a site's terms of service still bind you if you agreed to them. Fyre is a tool; the responsibility for a given use sits with the person running it. If a project involves personal data at any scale, get advice before you start.

Cloud runs read robots.txt and honour disallow rules by default; you can override that for domains you own. Local extraction reads the page your browser has already loaded, so robots.txt does not apply in the same way — but the rate limiting defaults are deliberately conservative.