#Bridge mode by Chrome extension

The bridge mode in the Midscene Chrome extension is a tool that allows you to use local scripts to control the desktop version of Chrome. Your scripts can connect to either a new tab or the currently active tab.

Using the desktop version of Chrome allows you to reuse all cookies, plugins, page status, and everything else you want. You can work with automation scripts to complete your tasks. This mode is commonly referred to as 'man-in-the-loop' in the context of automation.

#Set up API keys for model

Set your model configs into the environment variables. You may refer to Model strategy for more details.

export MIDSCENE_MODEL_BASE_URL="https://replace-with-your-model-service-url/v1"
export MIDSCENE_MODEL_API_KEY="replace-with-your-api-key"
export MIDSCENE_MODEL_NAME="replace-with-your-model-name"
export MIDSCENE_MODEL_FAMILY="replace-with-your-model-family"

For more configuration details, please refer to Model strategy and Model configuration.

In bridge mode, the AI models configs should be set in the Node.js side instead of the browser side.

#Get started

#Step 1. Install Midscene extension from Chrome web store

Install Midscene extension from Chrome web store

#Step 2. Install dependencies

npm install @midscene/web tsx --save-dev

yarn add @midscene/web tsx --save-dev

pnpm add @midscene/web tsx --save-dev

bun add @midscene/web tsx --save-dev

deno add npm:@midscene/web npm:tsx --save-dev

#Step 3. Write scripts

Write and save the following code as ./demo-new-tab.ts.

import { AgentOverChromeBridge } from "@midscene/web/bridge-mode";

const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
Promise.resolve(
  (async () => {
    const agent = new AgentOverChromeBridge();

    // This will connect to a new tab on your desktop Chrome
    await agent.connectNewTabWithUrl("https://www.bing.com");

    // these are the same as normal Midscene agent
    await agent.ai('type "AI 101" and hit Enter');
    await sleep(3000);

    await agent.aiAssert("there are some search results");
    await agent.destroy();
  })()
);

#Step 4. Run the script

Run your scripts

tsx demo-new-tab.ts

After running the script, the Chrome extension will pop up a confirmation dialog asking whether to allow the connection. Click "Allow" to allow the current connection, or click "Always Allow" to automatically allow all future connection requests (can be reset in the Bridge Mode panel). You should then see a new tab opened in your desktop Chrome, controlled by your scripts.

#Use bridge mode in YAML script

Yaml scripts is a way for developers to write automation scripts in yaml format, which is easy to read and write comparing to javascript.

To use bridge mode in yaml script, set the bridgeMode property in the web section. If you want to use the current tab, set it to currentTab, otherwise set it to newTabWithUrl.

Set closeNewTabsAfterDisconnect to true if you want to close the newly created tabs when the bridge is destroyed. This is optional and the default value is false.

For example, the following script will open a new tab by Chrome extension bridge:

web:
  url: https://www.bing.com
+ bridgeMode: newTabWithUrl
+ closeNewTabsAfterDisconnect: true
tasks:

Run the script:

midscene ./bing.yaml

After the script starts, click "Allow" in the confirmation dialog to proceed.

#Unsupported options

In bridge mode, these options will be ignored (they will follow your desktop browser's settings):

• userAgent
• viewportWidth
• viewportHeight
• deviceScaleFactor
• waitForNetworkIdle
• cookie

#Remote Access Configuration

By default, the Bridge Server only listens on 127.0.0.1, allowing only local Chrome extension connections. If you need cross-machine communication (e.g., server on machine A, browser on machine B), you can enable remote access:

Server Side (Node.js Script):

// Enable remote access (recommended)
const agent = new AgentOverChromeBridge({
  allowRemoteAccess: true  // Listen on 0.0.0.0:3766
});

// Or specify a specific network interface
const agent = new AgentOverChromeBridge({
  host: '192.168.1.100',  // Listen on specific IP
  port: 3766
});

Client Side (Chrome Extension):

1. Open the Chrome extension's Bridge Mode page
2. Fill in the server address in the "Bridge Server URL" input field
   • Local mode: ws://localhost:3766 (default)
   • Remote mode: ws://192.168.1.100:3766 (replace with your server IP)
3. Run your script and click "Allow" in the confirmation dialog

#FAQ

• Where should I config the model parameters (like MIDSCENE_MODEL_API_KEY), in the browser or in the terminal?

When using bridge mode, you should config the model parameters in the terminal. For more configuration details, please refer to Model strategy.

#More

• For every Agent method, check the API reference.
• For the full Chrome Bridge API surface, see API reference (Web).
• Demo project
  • Bridge mode demo: https://github.com/web-infra-dev/midscene-example/blob/main/bridge-mode-demo