Can it scrape pages behind a login?

Yes. web_login opens a real browser window where you sign in yourself; the AI never sees your credentials. The session is saved locally and reused, so the AI can read the logged-in page on later runs.

Does it run on a schedule automatically?

No unattended timer — you trigger a run whenever you want it, or wire the recipe into your own scheduler or an AI routine. Any recipe that would submit something previews first and waits for your confirm.

How does it tell me what changed?

Every run is stored locally. On a rerun the AI compares the fresh rows against the previous run and surfaces only the new, changed, or removed ones — not the whole table again.

Make Your AI Pull Fresh Data From Any Website on Your Mac

You keep going back to the same web page — a listings board, a supplier's prices, a client portal's table, a dashboard — copying the same numbers by hand. There's no export button and no API. LMCP lets an AI do that pull for you on your Mac, and save it so the next run is one sentence. It works through LMCP, a free, native macOS MCP server with a built-in browser — so it can even read pages that live behind a login.

How it works

The pattern is get it working once, then save it as a recipe. LMCP's web tools are agnostic — the same handful work on any site:

web_login — if the page needs a sign-in, a real browser window opens and you log in (password, 2FA — never the AI). The session is saved on your Mac and reused, so you don't log in again.
web_navigate / web_read — go to the data page and read its content, or a compact list of its elements so the AI can find the right rows.
web_extract — pull the rows into clean, structured fields (title, price, link…), null where a field is missing.
recipe_save / recipe_run — save the working sequence as a named recipe and replay it anytime with one line. recipe_runs keeps the history, so the AI can tell you what changed since last time instead of dumping the whole table.

Try a prompt like: "Open this page, pull every listing into a table — title, price and link — show me the table, then save it as a recipe called 'daily listings' so I can rerun it tomorrow."

The real value: what changed

A one-off scrape is easy. The point of a recurring one is the diff. Because every run is stored, on the next run your AI compares the fresh rows against the last ones and surfaces only what's new, changed, or gone — the update you actually wanted, not a wall of rows you have to re-read.

Does it run on a schedule by itself?

LMCP doesn't run recipes on an unattended timer — you trigger a run whenever you want it ("run my listings recipe"), or wire it into your own scheduler or an AI routine. That keeps you in control: a scrape happens because you asked, and any recipe that would ever submit something previews first and waits for your confirm.

Is this safe and private?

You sign in yourself, in a real window — the AI never handles your password. The browser, its saved session, and every run's data stay on your Mac; nothing is uploaded to a scraping service or a third-party cloud. This is the same local-first model LMCP uses for everything else. Note that scraping some sites may go against their terms of service, so use it thoughtfully on pages you're allowed to read.

Which AI assistants can do this?

Desktop clients — Claude Desktop, Cursor, VS Code, Windsurf and Zed auto-configure via local stdio.
Web AIs — ChatGPT, Claude.ai (web), Grok and Perplexity connect through the LMCP Cloud Relay. Even then, the browser runs on your Mac and your login never leaves it.

Stop copying the same page by hand. Download LMCP, point your AI at the page, and save the pull as a recipe you rerun in one line.