The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the MCP Browser Kit listing page.
🚀 On the
mainbranch? You're viewing the bleeding-edge dev docs! For other versions, check out therelease/*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
Add MCP Browser Kit to your MCP Client:
By default the server use stdio transport, alternatively you can use http transport:
Then point your MCP client at the URL instead of a command:
Security: there's no auth yet, so
--http-hostdefaults to127.0.0.1(loopback only). Only pass--http-host 0.0.0.0(or a LAN address) if you understand that anyone who can reach that host/port can control your browser.
Choose the right extension build for your browser:
Download the latest compatible build from The Latest Release.
Load the extension into a compatible browser and enable it.
Refresh open tabs to ensure extension scripts are loaded.
Start messaging on your MCP Client:
Optional, check User Notes for more information.
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)
| Browser | M2 build | M3 build |
|---|---|---|
| Chrome | ❌ | ✅ |
| Brave | ✅ | ✅ |
| Edge | ✅ | ✅ |
| Firefox | ✅ | ❌ |
| Safari | ✅ | ❌ |
.zip fileDeveloper modeLoad unpackedInstall Add-on From File.xpi file.zip fileDevelop > Show Extension Builder+ and select Add ExtensionInstall to install the extensionNote 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 21082 and 2769-2799 on your device network only.
A hosted deployment is available on Fronteir AI.