Let AI agents drive Microsoft Edge, over MCP

EdgePilot is an MCP server and Microsoft Edge extension for Windows. Each chat gets a labelled tab-group workspace or its own Edge profile, you can talk to the agent from the side panel, and sign-in goes through the Edge password manager without the agent ever seeing a password.

Download the latest release View on GitHub

Version 1.0.0 · Windows 10 / 11 · Free for noncommercial use

38MCP tools
2workspace modes: labels or a profile per chat
3MCP protocol versions supported
0npm dependencies

Animated EdgePilot demo built from real screenshots: labelled tab-group workspaces in Microsoft Edge, the side panel chat, workspaces and activity views, the sign-in approval window and the on-page indicator

Features

Built for using your everyday Edge with AI agents, several chats at once, with you in control.

Workspaces that stay

Every chat works in its own Edge tab group, labelled with the chat's name. The label survives Edge restarts, so tomorrow's chat in the same project picks up the same tabs.

A profile per chat, if you want

Keep every chat in one Edge with your usual sign-ins, or give a chat its own separate Edge profile with separate cookies, accounts and history, started automatically.

Chat from the side panel

The side panel has a chat per workspace. Messages reach the agent live where the client supports channel events, or with its next action; replies also show as Edge notifications.

Edge passwords, never exposed

You approve each sign-in in an Edge window; Edge's own password manager fills the login. Password values are masked in everything the agent can read.

You stay in control

Pause all agents, stop a single workspace, or press Stop on the on-page indicator. Block sites entirely. Every action is in the activity timeline.

38 MCP tools

Trusted mouse and keyboard input, screenshots, accessibility tree with refs, tables and links, console and network capture, emulation, PDF export, downloads, favorites and history.

Screenshots

The EdgePilot windows come in light and dark, following the theme of Edge. This page shows the ones that match yours.

EdgePilot side panel chat with the AI agent working in the research workspace — Chat with the agent of each workspace

EdgePilot side panel list of agent workspaces with live and idle state — Workspaces: show, stop, rename, close tabs

EdgePilot activity timeline listing every action the AI agents took — Activity timeline of every agent action

Three AI agent chats in one Microsoft Edge window, each in its own labelled tab group: research, docs-site and shop-checkout — Three chats in one Edge window, each in its own labelled tab group. The pill at the bottom right shows which chat is using the page.

EdgePilot sign-in approval window for filling a saved login from the Edge password manager — Approve a sign-in with the Edge password manager

EdgePilot question window where the agent asks you to decide or act — The agent asks you when it needs a decision, a CAPTCHA or a 2FA code

Install

Requirements: Windows 10 or 11, Microsoft Edge and Node.js 22 or newer (the installer offers to install it with winget).

Get EdgePilot

Run the one-line installer in PowerShell:
```
irm https://raw.githubusercontent.com/AndrasBogdanAndrei/EdgePilot/main/install.ps1 | iex
```
or download EdgePilot-1.0.0.zip from the latest release, unzip it and double-click install.cmd. The installer registers the bridge for Edge (current user only), connects the MCP clients it finds, copies the extension folder path to your clipboard and waits until Edge connects.

Run the installer yourself, from Explorer or a normal terminal. Some desktop apps run their terminals in a packaged (MSIX) sandbox with a private copy of the registry, and Edge would not see a bridge registered from there.
Load the extension in Edge

In every Edge profile you want agents to use: open edge://extensions, turn on Developer mode, click Load unpacked, paste the path and select the folder. Separate-profile mode needs nothing else.
Connect your MCP client

Add a stdio server to your MCP client (Cursor, VS Code, Windsurf and others):
```
{
  "mcpServers": {
    "edgepilot": {
      "command": "node",
      "args": ["C:\\Users\\you\\EdgePilot\\mcp\\server.js"]
    }
  }
}
```
Start a new chat and ask it to use Edge.

MCP tools

EdgePilot exposes 38 tools to the agent. Full descriptions in the README.

Workspaces & browsers

workspace list_connected_browsers select_browser list_edge_profiles launch_edge_profile browser_batch

Tabs & navigation

tabs_context tabs_create tabs_select tabs_close navigate

Input & vision

computer highlight

Reading

read_page find get_page_text get_links extract_tables

Forms & scripting

form_input javascript_tool page_storage file_upload wait_for handle_dialog

Debugging & testing

read_console_messages read_network_requests block_urls emulate performance_metrics resize_window save_pdf

Edge features

autofill_credentials downloads bookmarks history_search

Talking to you

ask_user chat_send chat_read

How it works

How EdgePilot works: AI chat to MCP server over stdio, MCP server to bridge over a named pipe with a token, bridge to the Edge extension over native messaging, extension to labelled tab groups over the DevTools protocol; the side panel chat sends your messages to the extension

Each chat starts its own MCP server; each Edge profile with the extension starts its own bridge. Bridges listen on a local named pipe protected by a random token. No network ports are opened, except for a few seconds when a separate profile is created. EdgePilot sends nothing to a server; page content the agent reads goes to your MCP client and the AI model it uses.

EdgePilot on-page indicator: a glowing frame and a Stop button on the page the AI agent is controlling — While an agent acts on a page, a soft glow and a Stop button appear for a few seconds.

FAQ

How do I let an AI agent control Microsoft Edge?

Install EdgePilot with install.cmd or the one-line PowerShell installer, load the extension folder in edge://extensions with Developer mode and Load unpacked, and add EdgePilot to your MCP client as a stdio server. Then start a new chat and ask the agent to use Edge. It opens its own labelled tab group and works there.

Which AI agents and MCP clients work with EdgePilot?

Any client that can start a local stdio MCP server, for example Cursor, VS Code, Windsurf or a command-line coding agent. EdgePilot answers MCP protocol versions 2024-11-05, 2025-03-26 and 2025-06-18.

Does the AI agent see my passwords?

No. The autofill_credentials tool asks for your approval in an Edge window the agent cannot click, and then the Edge password manager fills the fields. The agent only learns that the fields were filled. Password values are masked in page reads, scripts, console, network and storage output.

Can each AI chat use a different Edge profile or account?

Yes. In profile mode every chat gets its own Edge profile with separate cookies, accounts and history. In labels mode chats share one Edge profile and its sign-ins, each in its own tab group. A chat can also use one of your regular Edge profiles.

How do I stop an agent?

Press Stop on the on-page indicator, stop one workspace in the side panel, or pause all agents. You can also block sites so agents cannot read or control them.

Does EdgePilot work with Google Chrome, macOS or Linux?

No. EdgePilot is built for Microsoft Edge on Windows 10 and 11: the installer registers the bridge for Edge and the bridge uses Windows named pipes.

Is EdgePilot free?

It is free for any noncommercial use under the PolyForm Noncommercial License 1.0.0. For commercial use, open an issue on GitHub to ask for a license.

Download EdgePilot 1.0.0 Read the docs