Browse Bridge

com.browsebridgePublished by browsebridge.comOfficial publisherv1.0.0Updated Oct 29, 2026

Let AI agents observe and control Chrome tabs you explicitly share via Browse Bridge.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingBrowser Automation

Overview

AI-generated overview

Remote MCP server that lets an AI agent observe and control Chrome tabs you explicitly share through the Browse Bridge extension.

What you can do
  • List and inspect shared tabs, including control mode, URL, device status and remaining monthly quota
  • Observe a page as a semantic element tree and capture screenshots of the visible tab
  • Interact with pages: click, type, select options, press keys, hover, scroll and handle JavaScript dialogs
  • Navigate with URL, back, forward and reload, and pause with a wait
  • Manage control and approvals: release the tab to the human, read or cancel a pending approval
  • Read the signed-in account's Browse Bridge user id
When to use it
Useful when an agent needs to work in a real, logged-in Chrome session on sites you choose to share, for example filling forms, checking pages or walking through a flow, while you keep the ability to take control back or approve sensitive actions.
Requirements
A Browse Bridge account and a paid or free plan, the Browse Bridge Chrome extension signed in to the same account, and an API key starting with bbk_ sent as an Authorization Bearer header (BROWSEBRIDGE_API_KEY). The remote endpoint is a Cursor plugin or manual mcp.json config is used to connect.
Before you install
The API key is a secret and must be kept private; do not paste it into shared configs. The agent can click, type, navigate and accept dialogs in shared tabs, which may submit forms or change data. Sensitive sites and cross-origin navigations require human approval, and monthly action and screenshot quotas can be exhausted. Only tabs you explicitly enable are shared, and you can take control back at any time.

Installation

In SourceWeft

  1. Open Browse Bridge in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.browsebridge%2Fbrowse-bridge/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "browse-bridge": {
      "type": "http",
      "url": "https://mcp.browsebridge.com/mcp"
    }
  }
}

README

Browse Bridge for Cursor

Cursor Plugin that wires Browse Bridge remote MCP into Cursor so agents can observe and control browser tabs you have Explicitly Enabled in the Chrome extension.

Prerequisites

  1. Create an account at https://browsebridge.com/sign-up (plans: https://browsebridge.com/plans).
  2. Install the Browse Bridge Chrome extension from the Chrome Web Store and sign in with the same account.
  3. Sign in and open Connections to create an API key (starts with bbk_). Keep it secret.
  4. Cursor with plugin/MCP support.

Install (Marketplace / local)

Official Marketplace (after listing)

Install browse-bridge from the Cursor Marketplace and paste your API key when prompted (BROWSEBRIDGE_API_KEY).

Local test (before / without Marketplace)

bash
# Copy (do not symlink outside this folder)cp -R /path/to/browsebridge-cursor-plugin ~/.cursor/plugins/local/browse-bridge

Reload Window, open Customize, configure BROWSEBRIDGE_API_KEY, confirm MCP tools appear (browser_observe, browser_click, etc.).

Manual mcp.json snippet

json
{  "mcpServers": {    "browse-bridge": {      "url": "https://mcp.browsebridge.com/mcp",      "headers": {        "Authorization": "Bearer ${BROWSEBRIDGE_API_KEY}"      }    }  }}

Plugin variables only fill in inside the plugin, so for a manual config use your real key or ${env:BROWSEBRIDGE_API_KEY}.

Usage

  1. Open a normal website tab (not chrome://).
  2. Click the Browse Bridge toolbar icon, then Enable on the tab you want to share. Accept the confirmation and any Chrome permission prompt. Use Take control (or Ctrl+Shift+Period) to take the tab back at any time.
  3. In Cursor, use MCP tools such as browser_list_sessions, browser_observe, browser_click, browser_screenshot.
  4. Challenges / sensitive sites may pause the agent for human Take over or Approve.

Tools (20)

ToolWhat it does
browser_list_sessionsList Enabled shared tabs.
browser_get_statusControl mode, URL, deviceOnline, pending approvals, remaining monthly quota (actionsRemaining, screenshotsRemaining, quotaExceeded, quotaResetAt). Tools return QUOTA_EXCEEDED when a monthly quota is exhausted.
browser_observeSemantic page tree + observationId / elementIds.
browser_screenshotVisible-tab JPEG as MCP image content.
browser_clickClick an observed element. Optional button: "left" (default), "right", or "middle".
browser_typeSet a control's value (not a password).
browser_selectChoose a listed <option>.
browser_press_keyKey in the focused (or named) element.
browser_hovermouseover / mouseenter on an observed element.
browser_scrollScroll the page or an element into view.
browser_navigateGo to an allowed http(s) URL.
browser_backHistory back.
browser_forwardHistory forward.
browser_reloadReload the tab.
browser_waitPause 0–30000 ms.
browser_release_controlGive the tab back to the human (controlMode: "human").
browser_handle_dialogAccept or dismiss a pending JavaScript alert / confirm / prompt (action: accept|dismiss; optional promptText when accepting a prompt).
browser_get_approvalRead-only status of a pending approval (approvalId). Does not Approve, Deny, or cancel.
browser_cancel_approvalWithdraw a pending agent approval (approvalId).
get_profileRead-only Browse Bridge user id for the signed-in account (no email, tokens, cookies, or page content).

JavaScript dialogs

While the agent has control, a page alert / confirm / prompt stays pending until browser_handle_dialog (or about a 30-second timeout dismiss). Other click, type, and navigate calls while a dialog is open return DIALOG_PENDING. Native HTTP basic or digest sign-in prompts are not JavaScript dialogs (HTTP_AUTH_REQUIRED). The human completes or cancels them. Browse Bridge never types those credentials.

Approvals

Sensitive site gates click, type, key, select, and navigation. Those actions, and cross-origin navigations (including cross-origin link clicks), return APPROVAL_REQUIRED. The human Approves or Denies in the Chrome side panel. browser_get_approval reads a pending approval and does not change it. The agent can withdraw its own request with browser_cancel_approval (APPROVAL_CANCELLED — that is not a human Deny). An expired approval returns APPROVAL_EXPIRED; the next request for that action returns a fresh APPROVAL_REQUIRED. While an approval is pending, observe/screenshot/wait/get_status/list_sessions/release_control still run.

Configuration

VariableRequiredDescription
BROWSEBRIDGE_API_KEYYesAPI key from the Browse Bridge dashboard

Declared in .cursor-plugin/plugin.json → variables and referenced only as ${BROWSEBRIDGE_API_KEY} in mcp.json.

Privacy & security

See PRIVACY.md and SECURITY.md.

Repo layout

.cursor-plugin/plugin.jsonmcp.jsonassets/logo.svgassets/icon.pngREADME.mdLICENSEPRIVACY.mdSECURITY.mdSUPPORT.md

Source: README.md at commit 70c20fd

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestOct 29, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts