Skip to content

Quick Start

Once the extension is installed and the MCP server is configured, you're ready to go.

Try it out

Open your AI tool and try these prompts:

Navigation & automation:

Go to github.com and take a screenshot

Debugging:

Open https://example.com, check the browser console for errors, and read the network requests

Form automation:

Go to the login page and fill in the username field with "test@example.com"

GIF recording:

Record a GIF of me searching for "devbridge" on google.com

What happens

  1. Your AI tool calls a DevBridge MCP tool (e.g. navigate, screenshot, read_console)
  2. The MCP server forwards the request to the Chrome extension
  3. The extension executes the action in your active browser tab
  4. Results are returned to your AI tool

DevBridge shows a glowing indicator in the page while an action is running. You can stop any action at any time by clicking the stop button in the indicator.

Permission prompts

For sensitive operations (reading console logs, executing JavaScript, navigating to new domains), DevBridge will ask for your permission the first time. You can choose Just this once or Always for this domain.

→ Explore all 18 MCP tools

DevBridge — Browser Debugging & Automation via MCP