Question 1

The tool says it worked but nothing changed on the page

Accepted Answer

Beacon drives the tab you already have open, not a separate browser. A few sites ignore automated clicks or typing. Refresh the tab, reload the extension after an update, or finish that step yourself if the app is being stubborn.

Question 2

Page summaries use too much of my context

Accepted Answer

You get a short text map of the page, not screenshots or a full DOM dump. When you only need one area, ask for a smaller slice instead of the whole page every time.

Question 3

It feels slow going click by click

Accepted Answer

Use batched steps in one request when your client allows it. Observe when the page actually changes, not before every single action.

Question 4

Extension not connected or on the wrong tab

Accepted Answer

Install the extension, link your account from setup, and keep the site open in Chrome. Each snapshot lists your open tabs so you can target the right one.

Question 5

Is this using my real logins? Is that safe?

Accepted Answer

Yes. It uses your Chrome profile and the sessions you already signed into. Beacon does not store your site passwords. The relay only carries traffic for automation you start. Details are in our Privacy policy.

Question 6

Will it work on every site (banks, shopping, etc.)?

Accepted Answer

No product can promise that. Beacon is for everyday web apps you already use: admin tools, messaging, travel, dashboards. Sites that block automation need their official API or a human in the loop.

Question 7

Too many tools for the model to choose from

Accepted Answer

Beacon keeps a small set: read the page, act on it, navigate. Prefer one batched run over long chains of single clicks when you can.

Question 8

What is Beacon MCP?

Accepted Answer

Beacon MCP is a Chrome extension and relay that exposes your logged-in browser to AI agents through the Model Context Protocol. Tools like observe, click, type, and run work on stable n## control ids from a text dump of the page — built for accuracy in Cursor, Claude Code, and other MCP clients.

Question 9

Which MCP clients work with Beacon?

Accepted Answer

Any client that supports remote MCP over HTTP with a Bearer header on the same bcn_* key — not only Cursor or Claude Code. Paste the mcp.json from setup into your client's MCP settings, or use claude mcp add / Claude web connector if you use Anthropic. The optional beacon-browser skill on GitHub helps agents batch run steps and act by id.

Question 10

How is Beacon MCP different from Playwright MCP or screenshot tools?

Accepted Answer

Playwright MCP often drives a separate browser or huge snapshots. Beacon uses your existing Chrome profile and returns compact text observe maps with one id per control, so agents click the handle in the dump — not a label guess from a pixel or DOM soup.

Question 11

What makes a good browser MCP for production agents?

Accepted Answer

Stable identity on controls, verify-after-act, batched steps, and your real sessions (cookies, SSO). Beacon optimizes for that: observe → act by id → expect in run batches, with NEEDS_HUMAN when a login wall or captcha blocks automation.

Question 12

Does Beacon MCP work on localhost and SaaS dashboards?

Accepted Answer

Yes — that is the primary use case. Point Chrome at your app, connect MCP, and automate QA or workflows while logged in. It is not aimed at defeating every anti-bot wall on public merchants.

Question 13

Is Beacon browser automation or browser MCP?

Accepted Answer

Both labels fit. Browser automation is the outcome — click, type, navigate, fill forms, run checkouts in your Chrome. Browser MCP is how agents reach it: Model Context Protocol tools (observe, run, click) wired to the extension relay. Same product; MCP is the integration path for Cursor and Claude.

Question 14

How is AI browser automation different with Beacon?

Accepted Answer

Many stacks send screenshots or huge DOM trees and hope the model picks the right element. Beacon returns a short text map with stable ids per control, then tools take that id. That is built for agent browser automation you can verify — batch run with expect gates instead of blind click loops.

Question 15

Can agents automate the browser I already use for work?

Accepted Answer

Yes. Beacon is web automation in your existing Chrome profile — SSO, cookies, and tabs you opened. No separate bot browser. Your agent observes the tab you care about and acts there through MCP.

Question 16

Browser automation for QA, ops, and personal workflows?

Accepted Answer

Common uses: click-through QA on staging, repeating multi-step flows in admin tools, form fills, and shopping or travel sites you are already logged into. Use batched run steps and stop before irreversible actions (pay, send) unless you add explicit expect checks.

Question 17

What is a browser agent — and is Beacon one?

Accepted Answer

A browser agent is an AI that observes the web and takes actions (click, type, navigate) toward a goal. Beacon is the hands for that agent in your Chrome: MCP tools plus stable control ids so the model drives your real session, usually from Cursor or Claude Code.

Question 18

Browser agent vs cloud browser bots?

Accepted Answer

Cloud bots spin up a clean browser without your logins. A Beacon-backed browser agent uses your Chrome profile — same cookies, SSO, and tabs — which is what you want for internal tools and sites you already signed into. The agent loop stays observe → act by id → verify.

Many agents. One Chrome.

Five things you can do now.

Run several agents at once.

Sharper on real sites.

Every button stays clickable

Flight searches in one step

Agents always know where they are

Focus on one form

Pair, don’t share keys

Tabs land in the right group

Update, then just ask.

Also fixed