Browser Control MCP
Provides tools to control and read from a Firefox browser via an extension, including opening/closing and organizing tabs, searching browsing history, reading webpage text and links with per-domain consent, and finding/highlighting text in tabs.
Click on "Deploy 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., "@Browser Control MCPOpen Hacker News and summarize the top story and comments"
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.
FireMCP
English | Deutsch
FireMCP lets your AI assistant read your real Firefox: open tabs, live rendered pages, search within pages, history, bookmarks and screenshots. It consists of a Firefox add-on and a local MCP server, so it works with Claude Desktop, Claude Code and other MCP clients.
It reads what you already see in your browser, including pages behind a login and pages that only render with JavaScript, where a plain web fetch returns stale or empty content. It can open, close and arrange tabs, but it never clicks, types, submits forms or runs scripts of its own on pages.
Tools
Reading pages
Tool | What it does |
| Read an open tab, found by URL or title fragment, by tab ID, or the active tab |
| Read several open tabs in one call |
| Open a URL, wait until it has rendered and return its text |
| Open several URLs in background tabs, read them and close them again |
| Find text in a tab and return snippets with offsets |
| Meta tags, Open Graph, JSON-LD and headings of a page |
| The text you have selected in a tab |
| Full text and links of a tab (the original low level tool) |
| Screenshot of the visible part of a tab |
The reading tools return compact text, by default up to 40,000 characters per call with the offset to continue from. Options: format: "markdown" keeps headings, lists, links and tables, mainContentOnly leaves out navigation and sidebars, selector and excludeSelector pick parts of a page, and redactPersonalData masks e-mail addresses, phone numbers, IBANs and card numbers.
Browser data
Tool | What it does |
| Open tabs with state (active, unloaded, loading), filter and sort |
| The tab you are looking at |
| Details of one tab |
| Visited pages, newest first, filtered by words and age |
| Bookmarks with folder path and date added |
Tabs
Tool | What it does |
| Open a page in a new tab |
| Close tabs |
| Change the order of tabs |
| Put tabs into a named, colored tab group |
| Find and highlight text in a tab |
Related MCP server: blackmount-mcp
What stays under your control
Local only. The add-on talks to the MCP server on your computer over
127.0.0.1and::1, and only accepts commands signed with a secret key that only the two of them know. FireMCP has no server of its own and collects no telemetry.Consent per site. The add-on reads a page only after you have allowed its site once. History, bookmarks and find on page are optional permissions, asked for on first use. A screenshot needs a click on the FireMCP toolbar button in that tab.
Deny list. Sites on the list are never read or opened and are left out of history and bookmark results.
Switches and log. Every tool can be switched off in the add-on's settings, and the last 100 actions are logged there.
Your assistant sees whatever it reads. Pages can contain text written to mislead AI assistants, so keep an eye on what your assistant does with your browser, as with any MCP server.
Installation
You need Firefox 140 or later.
1. Firefox add-on
Open the latest release in Firefox and click firemcp-<version>.xpi. The add-on is signed by Mozilla and updates itself. Its settings page opens after the installation and shows the secret key that the MCP server needs.
2. MCP server
Claude Desktop: Download firemcp-<version>.dxt from the same release and open it, or drag it into the extensions page of Claude Desktop's settings. Enter the secret key under "Configure" and switch the extension on.
Claude Code (needs Node.js 22 or later):
git clone https://github.com/ollrich/firemcp.git
cd firemcp
npm install
npm run build
claude mcp add firemcp --scope user -e EXTENSION_SECRET=<secret> -- node "$PWD/mcp-server/dist/server.js"Other MCP clients: Build as above, then add the server to the client's configuration:
{
"mcpServers": {
"firemcp": {
"command": "node",
"args": ["/path/to/firemcp/mcp-server/dist/server.js"],
"env": { "EXTENSION_SECRET": "<secret>" }
}
}
}The connection to the add-on is up a few seconds after the server starts.
Settings
Variable | Default | Meaning |
| (required) | Secret key from the add-on's settings page |
|
| Port for the connection to the add-on; must match the add-on's settings |
|
|
|
| off |
|
Several MCP clients
Several clients can use the same Firefox at once, for example Claude Desktop and a few Claude Code sessions. The first server process for a port and secret owns the connection to the add-on; further processes with the same values pass their calls on to it. A second browser or Firefox profile gets its own port and secret.
The original add-on
FireMCP grew out of Browser Control MCP. The server also works with that add-on from addons.mozilla.org, with fewer features: no markdown, no selectors, no page metadata, selected text or bookmarks. Tools that need the FireMCP add-on say so.
Examples
"Read the open Jira tab and list the tickets assigned to me."
"Search my history for the article about night trains I read last week and summarize it."
"Open the three newest results on the conference page and compare their deadlines."
Development
npm install
npm run build # MCP server and add-on, the XPI lands in firefox-extension/web-ext-artifacts
npm test # server tests (node:test) and add-on tests (Jest)mcp-server: the MCP server (TypeScript, Node.js)firefox-extension: the Firefox add-on (Manifest V2), texts in_locales/enand_locales/decommon: message types shared by both
For a test without signing, load firefox-extension/manifest.json as a temporary add-on in about:debugging. Architecture, project rules and the release steps are in AGENTS.md.
Credits
FireMCP builds on the work of others:
Eyal Zach (eyalzh) wrote Browser Control MCP, the MCP server and Firefox add-on this project grew out of, including the tab screenshot tool (eyalzh/browser-control-mcp#59).
Kostiantyn Kugot (kkugot) added the singleton broker that lets several MCP clients share one browser, and the
get-current-tabandget-tab-metadatatools, based on pull requests by dsdshcym and Alex Kapranoff.
Their full history is part of this repository. FireMCP itself is maintained by Oliver Eichhof (ollrich).
License
MIT. Firefox is a trademark of the Mozilla Foundation; FireMCP is not affiliated with Mozilla.
This server cannot be deployed
Maintenance
Related MCP Connectors
Let AI agents observe and control Chrome tabs you explicitly share via Browse Bridge.
Web search, data extraction and controlled browser automation for AI assistants via OAuth.
Connect AI assistants to your approved computer for files, commands, browser and desktop tasks.
Connect AI agents to your own Chrome with scoped access, approvals, and verified task results.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to control and automate your Chrome browser directly, leveraging existing login states and configurations for tasks like content analysis, semantic search across tabs, screenshots, network monitoring, and interactive operations.12MIT

blackmount-mcpofficial
AlicenseNot gradedqualityAmaintenanceEnables AI assistants to access and search local browser history, bookmarks, open tabs, and downloads for personalized context.MIT- AlicenseCqualityCmaintenanceEnables AI assistants to read and drive a real, logged-in Firefox browser, including tabs, cookies, history, and site interactions, all through the Model Context Protocol.5210 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to access individual Firefox tabs in their real logged-in state with time-limited, clearly marked, and revocable sharing. Supports both view-only and full-control modes, including interaction, navigation, and automation of the shared tab.1MIT