Integrations / AI agent clients / Gemini CLI

A browser for Gemini CLI.

Gemini CLI can run MCP servers next to it. Add Browz and Gemini can open pages, read them, fill forms and take screenshots in isolated browser profiles, so its sessions never touch your own browser.

Terminalgemini mcp add --scope user browz /Applications/Browz.app/Contents/Resources/browz-mcp

Setup

Set it up.

  1. Install Browz and open it

    Download Browz; the MCP server ships inside it.

  2. Add Browz for your user

    Without --scope user, Gemini CLI adds the server to the current project only (.gemini/settings.json).

    Terminalgemini mcp add --scope user browz /Applications/Browz.app/Contents/Resources/browz-mcp
  3. Or edit settings.json

    Add the entry under mcpServers, keeping the rest of the file.

    ~/.gemini/settings.json{ "mcpServers": { "browz": { "command": "/Applications/Browz.app/Contents/Resources/browz-mcp", "args": [] } } }

    File: ~/.gemini/settings.json

  4. Check it is connected

    Run gemini mcp list, or /mcp inside Gemini CLI: Browz should show as connected, with its tools.

    Terminalgemini mcp list
  5. Remote (beta)

    Add the hosted server, then run /mcp auth browz in Gemini CLI to sign in.

    Terminalgemini mcp add --scope user --transport http browz https://mcp.gobrowz.com/mcp

Config format from Gemini CLI MCP servers.

Example

Collect a table from a public page.

Gemini reads the page as a snapshot of roles and names, so it can pull structured text without parsing HTML.

PromptUsing Browz, open a throwaway session for "release notes", go to https://example.com, read the page with a snapshot and give me its headings as a list. Close the session when done.

Gemini CLI asks before running each tool unless you trust the server; --trust on gemini mcp add skips that, so use it only if you are happy for Gemini to act without asking.

Good to know

Notes and tips.

  • The snippets use the macOS path of the server inside Browz. On Windows it is %LOCALAPPDATA%\Programs\Browz\browz-mcp.exe, on Linux /usr/lib/browz/browz-mcp; or use npx -y @browz/mcp, which finds it.
  • Which Google accounts and plans Gemini CLI serves is set by Google; check its documentation if sign-in fails.
  • The remote server at https://mcp.gobrowz.com/mcp is in free public beta: it needs the Browz app open with Remote control on, on a computer with a hardware security chip, and offers the profile, tab and page tools. See what it needs and what it offers.
  • Browz has to be installed and open on the same computer: the local MCP server drives the app’s own profiles through its local API, and reads the app’s credentials itself, so no token goes in the config.
  • A person completes sign-ins, 2FA codes and CAPTCHAs. The agent can pause with browz_request_human and hand you the profile’s window, then carry on in the same session. Browz never solves or bypasses CAPTCHAs.
  • Use agents only where each site’s terms allow automated use, on accounts you are entitled to use. Our acceptable use policy applies to agents the same as to people.
  • The MCP server is on every plan, Free included (5 profiles). How many agent sessions can be open at once depends on the plan: see pricing.

FAQ

Gemini CLI and Browz.

Project or user scope?

gemini mcp add writes to the project’s .gemini/settings.json by default. Add --scope user to make Browz available in every directory.

Can I pass environment variables to the server?

Yes, with -e KEY=value on gemini mcp add, for example to point BROWZ_DATA at a data folder other than ~/.browz.

Does Gemini see my Browz token?

No. The server inside Browz reads the app’s credentials itself; nothing secret goes in settings.json.

Get started

Download Browz. Every task, its own browser.

Then, on macOS or Linux, put the MCP server on your PATHcurl -fsSL https://gobrowz.com/agents/install.sh | sh

For Mac, Windows and Linux. Free for 5 profiles. Paid plans from $4.99 a month, with a 14-day refund on your first payment.