Automate Firefox browser interactions through Model Context Protocol for web testing, debugging, and automation tasks.
Core Capabilities:
Page Management: List, open, navigate, select (by index, URL, or title), and close browser tabs; navigate browser history backward and forward
Element Interaction: Click, hover, fill forms, drag-and-drop, and upload files using stable UIDs from DOM snapshots that survive minor DOM changes
DOM Inspection: Capture page snapshots with unique element identifiers for reliable automation
Network Monitoring: Always-on capture of all HTTP requests with filtering by URL, method, status code, resource type, XHR, and timing; detailed request inspection with headers and response data
Console Debugging: Capture, filter (by level, time range, source, content), and clear browser console messages
Visual Capture: Screenshot full pages or specific elements by UID as base64 PNGs
Dialog Handling: Accept or dismiss browser alerts, confirms, and prompts with optional text input
Browser Control: Set viewport dimensions, headless mode, custom Firefox profiles, and TLS certificate handling
Multi-format Output: Text (human-readable) and JSON (structured) formats
Cross-platform Support: Works with Firefox 100+ on macOS, Linux, and Windows via WebDriver BiDi
Enables browser automation and web interaction through Firefox via WebDriver BiDi, providing tools for page navigation, element interaction, network monitoring, screenshot capture, and console message access.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@firefox-devtools-mcptake a screenshot of the current page and list recent network requests"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Firefox DevTools MCP
Model Context Protocol server for automating Firefox via WebDriver BiDi (through Selenium WebDriver). Works with Claude Code, Claude Desktop, Cursor, Cline and other MCP clients.
Repository: https://github.com/freema/firefox-devtools-mcp
Note: This MCP server requires a local Firefox browser installation and cannot run on cloud hosting services like glama.ai. Use
npx firefox-devtools-mcp@latestto run locally, or use Docker with the provided Dockerfile.
Requirements
Node.js ≥ 20.19.0
Firefox 100+ installed (auto‑detected, or pass
--firefox-path)
Install and use with Claude Code (npx)
Recommended: use npx so you always run the latest published version from npm.
Option A — Claude Code CLI
claude mcp add firefox-devtools npx firefox-devtools-mcp@latestPass options either as args or env vars. Examples:
# Headless + viewport via args
claude mcp add firefox-devtools npx firefox-devtools-mcp@latest -- --headless --viewport 1280x720
# Or via environment variables
claude mcp add firefox-devtools npx firefox-devtools-mcp@latest \
--env START_URL=https://example.com \
--env FIREFOX_HEADLESS=trueOption B — Edit Claude Code settings JSON
Add to your Claude Code config file:
macOS:
~/Library/Application Support/Claude/Code/mcp_settings.jsonLinux:
~/.config/claude/code/mcp_settings.jsonWindows:
%APPDATA%\Claude\Code\mcp_settings.json
{
"mcpServers": {
"firefox-devtools": {
"command": "npx",
"args": ["-y", "firefox-devtools-mcp@latest", "--headless", "--viewport", "1280x720"],
"env": {
"START_URL": "about:home"
}
}
}
}Option C — Helper script (local dev build)
npm run setup
# Choose Claude Code; the script saves JSON to the right pathTry it with MCP Inspector
npx @modelcontextprotocol/inspector npx firefox-devtools-mcp@latest --start-url https://example.com --headlessThen call tools like:
list_pages,select_page,navigate_pagetake_snapshotthenclick_by_uid/fill_by_uidlist_network_requests(always‑on capture),get_network_requestscreenshot_page,list_console_messages
CLI options
You can pass flags or environment variables (names on the right):
--firefox-path— absolute path to Firefox binary--headless— run without UI (FIREFOX_HEADLESS=true)--viewport 1280x720— initial window size--profile-path— use a specific Firefox profile--firefox-arg— extra Firefox arguments (repeatable)--start-url— open this URL on start (START_URL)--accept-insecure-certs— ignore TLS errors (ACCEPT_INSECURE_CERTS=true)--connect-existing— attach to an already-running Firefox instead of launching a new one (CONNECT_EXISTING=true)--marionette-port— Marionette port for connect-existing mode, default 2828 (MARIONETTE_PORT)
Connect to existing Firefox
Use --connect-existing to automate your real browsing session — with cookies, logins, and open tabs intact:
# Start Firefox with Marionette enabled
firefox --marionette
# Run the MCP server
npx firefox-devtools-mcp --connect-existing --marionette-port 2828Or set marionette.enabled to true in about:config (or user.js) to enable Marionette on every launch.
BiDi-dependent features (console events, network events) are not available in connect-existing mode; all other features work normally.
Warning: Do not leave Marionette enabled during normal browsing. It sets
navigator.webdriver = trueand changes other browser fingerprint signals, which can trigger bot detection on sites protected by Cloudflare, Akamai, etc. Only enable Marionette when you need MCP automation, then restart Firefox normally afterward.
Tool overview
Pages: list/new/navigate/select/close
Snapshot/UID: take/resolve/clear
Input: click/hover/fill/drag/upload/form fill
Network: list/get (ID‑first, filters, always‑on capture)
Console: list/clear
Screenshot: page/by uid (with optional
saveTofor CLI environments)Utilities: accept/dismiss dialog, history back/forward, set viewport
Screenshot optimization for Claude Code
When using screenshots in Claude Code CLI, the base64 image data can consume significant context.
Use the saveTo parameter to save screenshots to disk instead:
screenshot_page({ saveTo: "/tmp/page.png" })
screenshot_by_uid({ uid: "abc123", saveTo: "/tmp/element.png" })The file can then be viewed with Claude Code's Read tool without impacting context size.
Local development
npm install
npm run build
# Run with Inspector against local build
npx @modelcontextprotocol/inspector node dist/index.js --headless --viewport 1280x720
# Or run in dev with hot reload
npm run inspector:devTroubleshooting
Firefox not found: pass
--firefox-path "/Applications/Firefox.app/Contents/MacOS/firefox"(macOS) or the correct path on your OS.First run is slow: Selenium sets up the BiDi session; subsequent runs are faster.
Stale UIDs after navigation: take a fresh snapshot (
take_snapshot) before using UID tools.Windows 10: Error during discovery for MCP server 'firefox-devtools': MCP error -32000: Connection closed
Solution 1 Call using
cmd(For more info https://github.com/modelcontextprotocol/servers/issues/1082#issuecomment-2791786310)"mcpServers": { "firefox-devtools": { "command": "cmd", "args": ["/c", "npx", "-y", "firefox-devtools-mcp@latest"] } }The Key Change: On Windows, running a Node.js package via
npxoften requires thecmd /cprefix to be executed correctly from within another process like VSCode's extension host. Therefore,"command": "npx"was replaced with"command": "cmd", and the actualnpxcommand was moved into the"args"array, preceded by"/c". This fix allows Windows to interpret the command correctly and launch the server.Solution 2 Instead of another layer of shell you can write the absolute path to
npx:"mcpServers": { "firefox-devtools": { "command": "C:\\nvm4w\\nodejs\\npx.ps1", "args": ["-y", "firefox-devtools-mcp@latest"] } }Note: The path above is an example. You must adjust it to match the actual location of
npxon your machine. Depending on your setup, the file extension might be.cmd,.bat, or.exerather than.ps1. Also, ensure you use double backslashes (\\) as path delimiters, as required by the JSON format.
Versioning
Pre‑1.0 API: versions start at
0.x. Use@latestwith npx for the newest release.
CI and Release
GitHub Actions for CI, Release, and npm publish are included. See docs/ci-and-release.md for details and required secrets.
Author
Created by Tomáš Grasl
Resources
Looking for Admin?
Admins can modify the Dockerfile, update the server description, and track usage metrics. If you are the server author, to access the admin panel.