ie-mcp

Give an LLM the ability to drive a legacy IE-only web application.

⚠️ Status: alpha / work in progress. This project is under active development. The tool surface and configuration may change between versions, and breaking changes can land without notice until 1.0.0. Issues and PRs welcome — see Development and Roadmap.

ie-mcp is a Model Context Protocol server that automates Microsoft Edge in IE mode (the Trident / legacy document-mode engine) via the Selenium IEDriver, and exposes it over MCP stdio so clients like Claude Code, Claude Desktop, or Codex can read, click, fill, and scrape any IE-only intranet app that nothing else can touch anymore.

The server is application-agnostic: it knows nothing about any specific site. You point it at a target through environment variables and the Edge IE-mode site list, and it gives the model a Playwright-style toolbox (auto-waiting locators, frame navigation, grid extraction, readiness probing) tuned for the quirks of the Trident engine.

Why this exists

Modern browser-automation tools (Playwright, Puppeteer, Selenium-on-Chromium) cannot render IE-only apps — the ones that depend on ActiveX, document.all, framesets, VBScript-era behaviours, or an enforced legacy document mode. Edge's IE mode is the last supported way to run them, but it is notoriously awkward to automate:

• IEDriver attach is flaky (Protected-Mode boundary crossings, "could not find IE window").

• The legacy engine rejects Selenium's modern JS atoms (el.text, Select, get_attribute).

• Old document modes have no window.JSON, so naive scripts throw 'JSON' is undefined.

• Frame-based apps lose state if the session is recreated.

ie-mcp works around all of these so the model gets a stable, high-level interface.

Related MCP server: Selenium MCP Server

Features

• One long-lived session kept alive across tool calls, so frame-based apps keep state.

• Auto-waiting locators (id / css / xpath / name / link_text / tag / class).

• Nested frame navigation — address frames-inside-frames with a path like "3/0".

• Trident-safe primitives — click, fill, select, hover, key-press, scroll, upload, dialogs, all implemented to survive the legacy JS engine.

• Readiness probing (ie_wait_ready) that waits for every same-origin frame's readyState to complete and the DOM to stop changing — handles slow AJAX/frameset grids.

• Grid extraction (ie_grid) that heuristically finds the real data table and returns header-keyed rows.

• Screenshots (full window or single element), JS execution, history navigation, resize.

• Cross-process single-browser lock so two MCP clients can't collide on one IE session.

• Orphan cleanup — enumerate and kill stray Edge IE-mode / IEDriver processes.

• No required pip install — selenium can be loaded from a vendored deps folder.

• Built-in --selftest to diagnose your setup before wiring up a client.

Requirements

Installation

git clone https://github.com/thomfilg/ie-mcp.git
cd ie-mcp

# install selenium (or vendor it — see "No-pip / vendored selenium" below)
pip install -r requirements.txt

Download IEDriverServer.exe (matching your Edge / selenium version) from the Selenium downloads page and note its path.

Verify the setup

Before wiring up an MCP client, run the built-in self-test. It checks dependencies and paths, then opens and closes a real IE-mode session and confirms the Trident engine is actually in use:

python ie_mcp.py --selftest

A passing run prints RESULT: PASS and an IE/Trident userAgent.

Configuration

All configuration is via environment variables — all optional:

Claude Desktop

Edit your claude_desktop_config.json (Windows: %APPDATA%\Claude\claude_desktop_config.json) and add:

{
  "mcpServers": {
    "ie-mcp": {
      "command": "python",
      "args": ["C:\\path\\to\\ie-mcp\\ie_mcp.py"],
      "env": {
        "IE_DRIVER_PATH": "C:\\path\\to\\IEDriverServer.exe",
        "IE_SITE_LIST": "C:\\path\\to\\ie-mode-site-list.xml",
        "IE_DEFAULT_URL": "http://your-legacy-app/"
      }
    }
  }
}

Claude Code

claude mcp add ie-mcp -- python C:\path\to\ie-mcp\ie_mcp.py

…or add the same block as above to your .mcp.json / Claude Code MCP config.

Codex (and other stdio MCP clients)

Point the client at python ie_mcp.py as a stdio MCP server, passing the same env vars.

Tools

Working with frames

Many legacy apps are framesets. Use ie_frames to enumerate them, then pass frame to most tools. A nested path reaches frames-inside-frames — e.g. "3/0" is the first frame inside the fourth frame.

No-pip / vendored selenium

On locked-down or offline machines you can run without a global pip install. Drop the selenium package (and its deps) into a folder and point IE_PYDEPS at it:

pip install --target ../.pydeps "selenium>=4.14.0,<5"

By default the server looks for ../.pydeps relative to ie_mcp.py, so the MCP protocol itself has zero pip dependencies (newline-delimited JSON-RPC 2.0 is implemented inline).

How IE mode is reached

When IE_SITE_LIST is set, the server self-heals the HKCU Edge policy (SOFTWARE\Policies\Microsoft\Edge) so the listed sites open in IE mode:

• InternetExplorerIntegrationLevel = 1

• InternetExplorerIntegrationSiteList = file:///…/your-site-list.xml

• InternetExplorerIntegrationReloadInIEModeAllowed = 1

These are written under HKCU (no admin needed). If the key isn't writable, the server logs the exact values to set manually. When IE_SITE_LIST is unset, the server manages no policy and assumes Edge is already configured for IE mode.

Session creation navigates to the target URL during session start — the only reliable way to cross the Protected-Mode boundary into IE mode without the driver losing the browser.

Troubleshooting

Development

This is a single-file server (ie_mcp.py) with no build step — clone, install selenium, and run.

git clone https://github.com/thomfilg/ie-mcp.git
cd ie-mcp
pip install -r requirements.txt

# diagnose deps/paths and open a real IE-mode session
python ie_mcp.py --selftest

Project layout

• ie_mcp.py — the entire server: config, the IEDriver wrapper (IeSession), one t_* function per tool, the TOOLS registry, and the stdio JSON-RPC loop.

• requirements.txt — runtime deps (just selenium).

Adding a tool

1. Write a t_<name>(args) function that returns text_result(...) (or an image result).

2. Append an entry to the TOOLS list with name, description, inputSchema, and fn.

3. Keep it Trident-safe: prefer direct arguments[0].innerText / getAttribute over Selenium's JS atoms, and never rely on window.JSON inside injected scripts (IE7/quirks document modes don't have it — return delimited strings and parse them in Python).

4. Re-run --selftest, then exercise the tool from an MCP client against a real IE-mode app.

Debugging

• Set IE_LOG_FILE to capture the [ie-mcp] stderr log to a file.

• Use ie_browsers / ie_kill_orphans to inspect and clean up stray Edge/IEDriver processes.

• Set IE_NO_LOCK=1 while iterating to bypass the single-browser lock.

Contributing

Bug reports and PRs are welcome. Please:

• Keep the server single-file and dependency-light (selenium is the only runtime dep).

• Match the existing tool conventions (auto-waiting find, frame arg, text_result).

• Note any IE-mode / Trident quirk you worked around in a code comment — they're rarely obvious.

Roadmap

Planned / in progress (subject to change while in alpha):

• Multi-tab / multiple window-handle support.

• Cookie and localStorage inspection tools.

• Richer ie_grid (pagination + virtualized-grid scrolling helpers).

• Optional structured (JSON) tool results alongside text.

• Configurable per-tool default waits.

• Packaged release + versioned tags once the tool surface stabilizes (1.0.0).

License

MIT © 2026 thomfilg