MCP Browser Kit

What is MCP Browser Kit about?

MCP Browser Kit provides an MCP server and corresponding browser extensions that let AI assistants interact with local browsers, performing actions such as clicking, navigating, or gathering information directly from the user's desktop environment.

How to use MCP Browser Kit?

1. Add the server to your MCP client configuration:

{
  "mcpServers": {
    "browser-kit": {
      "command": "npx",
      "args": ["@mcp-browser-kit/server@latest"]
    }
  }
}

2. Choose a compatible extension build (M2 or M3) based on your browser.
3. Download the appropriate build from the latest GitHub release.
4. Load the extension into the browser (instructions differ for Chromium‑based browsers, Firefox, and Safari).
5. Refresh open tabs so the extension scripts are injected.
6. Send commands to the AI assistant using the browser-kit server, e.g., Use browser-kit, star the last open GitHub repo on my browser.
7. (Optional) Review the User Notes for security and profiling tips.

Key Features

• Cross‑browser support: Chrome, Brave, Edge, Firefox, Safari (different M2/M3 compatibility).
• Two extension builds: M2 offers more functionality; M3 is a lightweight alternative.
• Simple MCP server launch via npx.
• Hosted deployment available on Fronteir AI.
• Transparent communication on local ports 59089 and 2769‑2799.
• No built‑in authentication – encourages isolated browser profiles for safety.

Use Cases

• Automating routine web tasks (e.g., starring a repository, filling forms).
• Enabling AI agents to browse, scrape, or summarize live web content.
• Integrating browser actions into larger AI‑driven workflows or RPA pipelines.
• Testing AI‑generated scripts against real browsers in a controlled environment.

FAQ

Which browsers support the M2 build?

• Brave, Edge, Firefox, Safari (Chrome does not).

What is the difference between M2 and M3 builds?

• M2 provides richer APIs and more actions; M3 is a slimmer version for browsers that cannot run M2.

How can I secure the server?

• Run it on a trusted network, keep the exposed ports local, and optionally use a separate browser profile or dedicated instance.

What ports does the server use?

• 59089 for the main service and a range of 2769‑2799 for auxiliary communication.

Is there a cloud‑hosted option?

• Yes, a hosted deployment is available via Fronteir AI.

MCP Browser Kit

🚀 On the main branch? You're viewing the bleeding-edge dev docs! For other versions, check out the release/* branches.

An MCP Server that enables AI assistants to interact with your local browsers.

https://github.com/user-attachments/assets/1fbf87fd-06d1-42bf-a06f-cc2bbdf375a8

Usage

1. Add MCP Browser Kit to your MCP Client:

   {
   	"mcpServers": {
   		"browser-kit": {
   			"command": "npx",
   			"args": ["@mcp-browser-kit/server@latest"]
   		}
   	}
   }
   

2. Choose the right extension build for your browser:

   • Check the Compatibility table below to see which build (M2 or M3) is compatible with your browser
   • Note that M2 builds offer more functionality than M3 builds, so prefer M2 if your browser supports both

3. Download the latest compatible build from The Latest Release.

4. Load the extension into a compatible browser and enable it.

5. Refresh open tabs to ensure extension scripts are loaded.

6. Start messaging on your MCP Client:

   Use browser-kit, star the last open GitHub repo on my browser
   

7. Optional, check User Notes for more information.

Compatibility table

The M2 build supports more functionalities than the M3 build. Extension file name patterns:

• M2 build:
  • Chromium: mcp_browser_kit_m2-<version>.zip (e.g., mcp_browser_kit_m2-5.0.0.zip)
  • Firefox: mcp_browser_kit_m2-<version>.xpi (e.g., mcp_browser_kit_m2-5.0.0.xpi)
• M3 build: mcp_browser_kit_m3-<version>.zip (e.g., mcp_browser_kit_m3-5.0.0.zip)

Load Extension

• Chromium-based browsers (Chrome, Brave, Edge)
  1. Unzip the downloaded .zip file
  2. Open chrome://extensions/
  3. Enable Developer mode
  4. Click Load unpacked
  5. Select the unpacked extension folder
• Firefox
  1. Open about:addons
  2. Click the gear icon and select Install Add-on From File
  3. Select the downloaded .xpi file
• Safari
  1. Unzip the downloaded .zip file
  2. Open Develop > Show Extension Builder
  3. Click + and select Add Extension
  4. Select the unpacked extension folder
  5. Click Install to install the extension

User Notes

Note for Alpha stage: Consider using a separate browser profile or dedicated browser instance with this MCP to prevent sensitive data from being unintentionally exposed to AI model providers.

Security: BrowserKit currently lacks authentication for incoming requests. Keep ports 59089 and 2769-2799 on your device network only.

Hosted deployment

A hosted deployment is available on Fronteir AI.