zen-browser-mcp
Allows AI agents to control a live Firefox browser tab, including navigating to URLs, inspecting and clicking elements, typing into inputs, scrolling, and running custom JavaScript.
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., "@zen-browser-mcpNavigate to Hacker News and click the top story"
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.
π Zen Browser MCP
Drive your live Zen Browser (and Firefox) tabs directly from AI Agents (Claude Code, Oh My Pi, Cursor, Zed) via the Model Context Protocol (MCP).
No Chromium required. No heavy vision/screenshot models. Pure DOM-level interaction with zero token waste.
β¨ Features
π¦ Native Zen Browser & Firefox Support: Built specifically for Gecko using a lightweight WebExtension (Manifest V2).
β‘ Lightweight & Blazing Fast: Communicates over local WebSockets (
127.0.0.1:9876). Actions execute in milliseconds.π― Visual Feedback: When the agent clicks an element, it glows with a bright yellow outline on your screen so you can watch it work.
π§ React & Vue Reactive Input: Input values are dispatched through prototype setters, guaranteeing that modern single-page apps (SPAs) register form changes.
π 100% Private & Local: All communication stays on your machine loopback. Zero cloud tracking, zero screenshots sent to LLMs.
π οΈ Dual Interface: Use it as a native MCP Server for AI models or as a standalone
zen-agentCLI tool in your terminal.
Related MCP server: mcp-zen
ποΈ Architecture
βββββββββββββββββββββββββββββ
β AI Agent β
β (Claude Code / OMP / ...) β
βββββββββββββββ¬ββββββββββββββ
β stdio (JSON-RPC 2.0)
βββββββββββββββΌββββββββββββββ
β zen-browser-mcp β
β (mcp-server.ts) β
βββββββββββββββ¬ββββββββββββββ
β HTTP REST (127.0.0.1:9876)
βββββββββββββββΌββββββββββββββ
β Zen Bridge Server β
β (Bun WebSocket server) β
βββββββββββββββ²ββββββββββββββ
β WebSocket (ws://127.0.0.1:9876)
βββββββββββββββΌββββββββββββββ
β Zen Agent WebExtension β
β (Zen Browser / Firefox) β
βββββββββββββββββββββββββββββπ Quick Start (1 Minute)
1. Clone & Run Installer
git clone https://github.com/KadirBerkpolat1/zen-browser-mcp.git
cd zen-browser-mcp
./install.sh(If you don't have Bun installed, the script will automatically install it for you).
2. Start the Bridge Server
Run the server in the background:
nohup bun run server/bridge.ts serve >/dev/null 2>&1 &(Or keep it open in a terminal window: zen-agent serve).
3. Load Extension into Zen Browser
Open Zen Browser and navigate to:
about:debugging#/runtime/this-firefoxClick "Load Temporary Add-on..." (Bu Firefox'a GeΓ§ici Eklenti YΓΌkle...).
Select
extension/manifest.json(or the packagedzen-agent.xpi) inside the cloned repo.
4. Verify Connection
In your terminal, run:
zen-agent statusYou should see:
β
Zen Browser baΔlΔ±!
BaΕlΔ±k : YouTube - Home
URL : https://www.youtube.comπ AI Agent Configuration (MCP)
Claude Code
Run the native CLI command:
claude mcp add zen-browser bun run /absolute/path/to/zen-browser-mcp/mcp-server.tsCursor / Oh My Pi (OMP) / Zed
Add the server to your mcp.json (~/.omp/agent/mcp.json or .cursor/mcp.json):
{
"mcpServers": {
"zen-browser": {
"command": "bun",
"args": ["run", "/absolute/path/to/zen-browser-mcp/mcp-server.ts"]
}
}
}π§° Available MCP Tools
When connected, your AI agent has direct access to these typed tools:
Tool | Parameters | Description |
| (none) | Returns connection status, current tab title, and active URL. |
|
| Navigates the active Zen tab to the specified URL. |
| (none) | Scans visible buttons, links, search inputs, and returns numbered |
|
| Highlights and clicks an element by |
|
| Focuses an input, types text, and optionally triggers Enter/submit. |
|
| Smoothly scrolls the active page ( |
|
| Runs custom JavaScript in the page context and returns the result. |
π» Standalone CLI Usage (zen-agent)
You can also control Zen Browser directly from your terminal:
# Check connection
zen-agent status
# Navigate to website
zen-agent goto "https://www.amazon.com"
# Inspect actionable buttons and fields
zen-agent inspect
# Click by index number or text
zen-agent click 4
zen-agent click "Add to Cart"
# Type into search field and submit
zen-agent type "input[type='search']" "mechanical keyboard" --enter
# Scroll down
zen-agent scroll down 600πΉπ· TΓΌrkΓ§e Γzet
Bu araΓ§, Zen Browser (veya Firefox) kullanan geliΕtiricilerin aΓ§Δ±k olan sekmelerini Claude Code, OMP ve Cursor gibi yapay zeka ajanlarΔ±na baΔlamasΔ±nΔ± saΔlar.
Chromium ΕartΔ± yok: Zen Browser'Δ±n kendi motoruyla uyumludur.
Ekran gΓΆrΓΌntΓΌsΓΌ Γ§ekmez: SayfayΔ± HTML kodu ΓΌzerinden okur, kotayΔ± tΓΌketmez ve anΔ±nda tΔ±klar.
CanlΔ± Δ°zleme: Yapay zekanΔ±n tΔ±kladΔ±ΔΔ± butonlarΔ±n etrafΔ±nda sarΔ± Δ±ΕΔ±k yanar, ne yaptΔ±ΔΔ±nΔ± canlΔ± izleyebilirsiniz.
Kurulum:
git clone https://github.com/KadirBerkpolat1/zen-browser-mcp.git
cd zen-browser-mcp
./install.shπ‘οΈ Security & Privacy
Safe By Design: The extension connects strictly to
127.0.0.1:9876. No external connections are made.Prompt Safety Rule: Agents are instructed never to click final payment or checkout confirmation buttons without explicit user consent.
π License
MIT License Β© 2026 Kadir Berk Polat
This server cannot be deployed
Maintenance
Related MCP Connectors
Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.
Live browser debugging for AI assistants β DOM, console, network via MCP.
Hyperbrowser MCP β wraps the Hyperbrowser AI-agent browsing API
Scrape, crawl and search the web for AI agents via MCP.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to control the Google Chrome browser through a Node.js WebSocket bridge and a dedicated browser extension. It provides tools for capturing screenshots, executing JavaScript, managing tabs, and extracting page content via the MCP protocol.2-
- AlicenseNot gradedqualityBmaintenanceLets MCP clients control a live Zen/Firefox browser to navigate, click, fill forms, screenshot, and execute JavaScript through a persistent server and browser extension.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI to control a real browser through MCP tools for clicking, typing, navigation, screenshots, and more. It supports a follow mode that tracks the active tab, plus fixed mode for controlling specific tabs.153 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables local opencode agents to control a live Chrome browser via MCP tools, including tab management, JavaScript execution, clicking, form filling, page reading, screenshots, and console log retrieval.MIT