# How to let Claude control a browser > Let Claude control a browser with the Claude in Chrome extension, or with an MCP server in Claude Desktop or Claude Code. Which to pick, and how to set each up. Source: https://mosaicbrowser.com/guides/let-claude-control-a-browser ## How to let Claude control a browser To let Claude control a browser, either install Anthropic's Claude in Chrome extension, which drives your own Chrome on paid Claude plans, or connect Claude Desktop or Claude Code to an MCP server that drives a browser. Mosaic's MCP server gives Claude separate browser profiles, each with its own cookies and proxy. ![Hand Claude a browser of its own, beside a screenshot: the Mosaic MCP server: let an AI assistant manage profiles, proxies and launches](https://mosaicbrowser.com/covers/let-claude-control-a-browser.webp) There are two honest ways to let Claude control a browser, and they differ in whose browser Claude ends up driving. The extension route puts Claude inside the Chrome you already use, signed in as you. The MCP route hands Claude a browser that a server controls, which can be a throwaway, a persistent profile, or one of several profiles kept apart from each other. Pick by what Claude should be allowed to touch. ## Option 1: Claude in Chrome, inside your own browser Claude in Chrome is Anthropic's extension. Its help page describes it as an extension "that allows Claude to read, click, and navigate websites alongside you", available on paid plans, from the Chrome side panel and from Claude Cowork and Claude Code ([Claude Help Center](https://support.claude.com/en/articles/12012173-getting-started-with-claude-in-chrome), read 2 November 2026). To use it from Claude Desktop, the same page says to open Settings, then Customize, then Connectors, find Claude in Chrome and click Configure. The trade is in that first sentence: it works alongside you, in your browser. Every account you are signed in to is in reach, and Anthropic's own page says the extension "is still risky" and asks you to read its safety guidance first. For tasks on your own accounts while you watch, it is the shortest path. ## Option 2: an MCP server that drives a browser The Model Context Protocol lets Claude Desktop and Claude Code call tools a local program offers. A browser MCP server turns "open this page and press Sign in" into tool calls. Microsoft's Playwright MCP is the common one: it reads pages as accessibility snapshots, keeps a persistent profile by default, and takes `--user-data-dir` for a different folder ([Playwright MCP](https://github.com/microsoft/playwright-mcp), read 2 November 2026). That gives Claude one browser, separate from yours. It is still one machine, one address and one set of cookies. When the work spans several accounts, one browser is where they meet. Mosaic is a desktop app Email yourself the link and open it on your computer. [How it works: MCP server](https://mosaicbrowser.com/features/mcp-server) ## How to let Claude control a browser with separate profiles Mosaic's [MCP server](https://mosaicbrowser.com/features/mcp-server) is built into the app and drives Mosaic profiles. Each profile has its own fingerprint, its own proxy exit and its own cookie jar, kept on your computer. Claude can create profiles, start them, read the page in front of each and click through it, from more than 150 tools. 1. In Mosaic, open Settings › MCP and turn on the server. It listens on `127.0.0.1`, port 39218 by default. 2. Open the API screen, go to Keys and make a key for Claude. Name it after what uses it, so you can revoke it alone. 3. Copy the config block Settings › MCP prints. It points at a small bridge script, `mosaic-mcp.mjs`, that Mosaic writes next to its data, because most clients launch a local command instead of calling HTTP. 4. For Claude Desktop, open its Settings, then Developer, then Edit Config, and paste the block into `claude_desktop_config.json` with your key. Quit Claude Desktop completely and open it again ([MCP docs](https://modelcontextprotocol.io/docs/develop/connect-local-servers), read 2 November 2026). 5. For Claude Code, add the same bridge from a terminal ([Claude Code docs](https://docs.anthropic.com/en/docs/claude-code/mcp), read 2 November 2026): ``` claude mcp add --env MOSAIC_API_KEY=msc_… --transport stdio mosaic \ -- node "/mosaic-mcp.mjs" ``` The bridge needs Node on the machine. If the key is wrong, or the plan does not include MCP, Claude gets Mosaic's sentence back as an error instead of a reply it cannot read. ![Mosaic Settings › MCP: the server switch, the port and the config block for a stdio client](https://mosaicbrowser.com/shots/settings-mcp.png) *Settings › MCP prints the block to paste, with the bridge path filled in* ### What to ask for first Start with something you can check by eye: "list my profiles in the Client work project", then "start Shop - Berlin 01 and take a snapshot of the page". `page_snapshot` returns the page as a tree of roles and names with a `ref` on everything Claude can press, a few hundred lines where the HTML runs to tens of thousands. A ref belongs to the snapshot that made it, so after a navigation an old one is refused by name instead of landing on whatever moved into its place. Clicks travel to the element along a human path and keys go in with human timing. None of the page tools enable the DevTools `Runtime` domain, because we measured that one call flipping deviceandbrowserinfo's verdict to `isBot=true`. ## Keep Claude's reach narrow The tools act without asking per call, so the limits sit around them. The server is off until you switch it on. Every request needs an API key, and the API activity screen shows what each key did. A destructive call with no scope, such as emptying the trash without naming what to empty, is refused instead of read as "all of it". A key reaches the whole library, not one project, so name the project Claude should work in when you ask, and revoke its key when the job is done. Sites still set their own rules about automated use, and an assistant clicking for you is automation. The [AI agents page](https://mosaicbrowser.com/use-cases/ai-agents) covers that, and the [guide to automating several profiles](https://mosaicbrowser.com/guides/automate-multiple-browser-profiles) does the same jobs from a script. The MCP server is part of Pro, $49 a month with a 14-day free trial, on the [pricing page](https://mosaicbrowser.com/pricing). ## Sources 1. [Claude Help Center: Get started with Claude in Chrome](https://support.claude.com/en/articles/12012173-getting-started-with-claude-in-chrome), read November 2, 2026 2. [Claude Code docs: Connect Claude Code to tools via MCP](https://docs.anthropic.com/en/docs/claude-code/mcp), read November 2, 2026 3. [Model Context Protocol: Connect to local MCP servers](https://modelcontextprotocol.io/docs/develop/connect-local-servers), read November 2, 2026 4. [Playwright MCP (GitHub)](https://github.com/microsoft/playwright-mcp), read November 2, 2026 ## Questions ### Do I need a paid Claude plan to let Claude control a browser? For Claude in Chrome, yes: Anthropic's help page lists it on the paid plans. Connecting Claude Desktop or Claude Code to an MCP server is a separate route, and the MCP server you pick sets its own terms. ### Can Claude use my logged-in accounts? With Claude in Chrome it works in your own browser, so it can reach whatever you are signed in to. With Mosaic it works in the profiles you give it, each with its own saved sign-ins, and nothing from your everyday browser. ### Does Claude ask before it clicks something? That depends on the client and its settings. Mosaic's tools do not ask for confirmation per action, so the protection is on the server side: it is off until you turn it on, needs an API key, and refuses a destructive call that names nothing to act on. ### Will the browsers Claude starts open on my screen? Yes. A profile Claude starts through Mosaic's MCP server opens a normal, visible window, so you can watch what it does. The REST API's start route can park a window off the screen with offscreen; the MCP start tools do not take that option as of 2 November 2026. ## Related [An anti-detect browser MCP server for your AI assistant](https://mosaicbrowser.com/features/mcp-server): Mosaic's anti-detect browser MCP server lets Claude or any MCP client create, launch and drive your profiles. 150+ tools, off by default, key-gated. [Anti-detect browser for AI agents](https://mosaicbrowser.com/use-cases/ai-agents): An anti-detect browser for AI agents gives each account the agent works in its own profile. Mosaic's MCP server and REST API let it drive them on your computer. [How to automate multiple browser profiles](https://mosaicbrowser.com/guides/automate-multiple-browser-profiles): Automate multiple browser profiles by giving each account a persistent profile, starting each from a script and attaching Playwright or Puppeteer over CDP. [Local first: your profiles stay on your computer](https://mosaicbrowser.com/features/local-first): Mosaic has no cloud copy of your profiles. Profiles, cookies and proxies stay on your computer, encrypted on disk, with app lock, daily backups and a trash. [MCP server for browser automation: what it is and which to use](https://mosaicbrowser.com/guides/mcp-server-for-browser-automation): An MCP server for browser automation turns page actions into tools an AI assistant can call. Playwright MCP, Chrome DevTools MCP and Mosaic compared.    ## Run this guide on your own accounts Every Mosaic profile is a fingerprint, a proxy exit and a cookie jar that agree with each other, kept on your computer. Free holds 3 profiles. Pro is $49 a month for any number. Mosaic is a desktop app Email yourself the link and open it on your computer.