@pokutuna/mcp-chrome-tabs
provides direct access to your browser's open tabs content. No additional fetching or authentication...
- Open the FastMCP connection interface (the dialog that appears after you click the "Install Now" button).
- In the connection form, set the command and args:
- Command: npx
- Args: -y @pokutuna/mcp-chrome-tabs@latest
- (If you want resource subscription, add an args entry such as --check-interval=3000 so the full args become: -y @pokutuna/mcp-chrome-tabs@latest --check-interval=3000)
Fill these values in the FastMCP connection interface fields before installing.
- ENV values: leave the ENV / environment variables section empty — this MCP does not require any API keys or environment tokens to run. If the interface shows ENV fields, do not provide any values (no key or secret is needed).
- Save / Install the connection in FastMCP (complete the install flow in the interface).
- Verify prerequisites on the host machine:
- macOS is required (this MCP uses AppleScript).
- Node.js 20 or newer must be installed.
- Enable Chrome Apple Events permission (required for tab access):
- In Chrome, enable "Allow JavaScript from Apple Events": View → Developer → Allow JavaScript from Apple Events.
- When you first run the MCP, macOS will prompt to grant automation permission to your MCP client (e.g., Claude Desktop). Click OK to allow.
- If you dismissed the prompt, enable it manually: System Settings → Privacy & Security → Automation → allow your MCP client to control Chrome.
- Optional browser customization (enter these as additional args in the FastMCP args field if needed):
- Change controlled application: --application-name="Safari" (or "Arc", "Google Chrome")
- Experimental browser mode: --experimental-browser=safari | arc | chrome
- After installation, test the server from your MCP client:
- Use the tool list_tabs or request the resource tab://current to confirm tabs are accessible.
- Troubleshooting quick checks:
- If you see "Current Tabs (0 tabs exists)", confirm "Allow JavaScript from Apple Events" is enabled and restart the browser.
- Ensure Node.js 20+ is available to the environment FastMCP runs in.
No environment variables are required — just fill the command/args in the FastMCP connection interface and follow the macOS/Chrome Apple Events steps above.
Quick Start
Choose Connection Type for
Authentication Required
Please sign in to use FastMCP hosted connections
Run MCP servers without
local setup or downtime
Access to 1,000+ ready-to-use MCP servers
Skip installation, maintenance, and trial-and-error.
No local setup or infra
Run MCP servers without Docker, ports, or tunnels.
Always online
Your MCP keeps working even when your laptop is off.
One secure URL
Use the same MCP from any agent, anywhere.
Secure by default
Encrypted connections. Secrets never stored locally.
Configuration for
Environment Variables
Please provide values for the following environment variables:
HTTP Headers
Please provide values for the following HTTP headers:
started!
The MCP server should open in . If it doesn't open automatically, please check that you have the application installed.
Copy and run this command in your terminal:
Make sure Gemini CLI is installed:
Visit Gemini CLI documentation for installation instructions.
Make sure Claude Code is installed:
Visit Claude Code documentation for installation instructions.
Installation Steps:
Configuration
Installation Failed
More for Browser Automation
View All →
Playwright Browser Automation
Experience fast, deterministic browser automation with Playwright MCP, a Model Context Protocol server that enables language models to interact with web pages using structured accessibility snapshots instead of images. It provides LLM-friendly automation without relying on vision models, enhancing reliability and speed. Playwright MCP supports diverse browser interactions such as clicking, typing, navigation, file uploads, and tab management. It offers modes optimized for accessibility snapshots or visual screenshots and supports persistent or isolated user profiles. Configurable with rich options, it empowers developers and AI agents to automate complex web tasks efficiently and precisely.
Chrome DevTools
Provides direct Chrome browser control through DevTools for web automation, debugging, and performance analysis using accessibility tree snapshots for reliable element targeting, automatic page event handling, and integrated performance tracing with actionable insights.
Firecrawl
Unlock powerful web data extraction with Firecrawl, turning any website into clean markdown or structured data. Firecrawl lets you crawl all accessible pages, scrape content in multiple formats, and extract structured data using AI-driven prompts and schemas. Its advanced features handle dynamic content, proxies, anti-bot measures, and media parsing, ensuring reliable and customizable data output. Whether mapping site URLs or batch scraping thousands of pages asynchronously, Firecrawl streamlines data gathering for AI applications, research, or automation with simple API calls and SDK support across multiple languages. Empower your projects with high-quality, LLM-ready web data.
Browser
Supercharge your browser tasks with AI-driven, local automation from Browser MCP. This project lets you control your own browser using leading AI tools, boosting speed and privacy by keeping all activity on your device. Enjoy seamless use of your current browser profile, remain logged into your services, and minimize bot detection thanks to a stealthy approach that mimics real user actions. Browser MCP is inspired by Playwright MCP and is designed for powerful, private, and efficient browser automation right on your machine.
Selenium WebDriver
Enables browser automation through Selenium WebDriver with support for Chrome, Firefox, and Edge browsers, providing navigation, element interaction, form handling, screenshot capture, JavaScript execution, and advanced actions for automated testing and web scraping tasks.
More for Automation
View All →FreeCAD
Enables AI-driven CAD modeling by providing a remote procedure call (RPC) server that allows programmatic control of FreeCAD, supporting operations like creating documents, inserting parts, editing objects, and executing Python code for generative design workflows.
Blender
Experience seamless AI-powered 3D modeling by connecting Blender with Claude AI via the Model Context Protocol. BlenderMCP enables two-way communication, allowing you to create, modify, and inspect 3D scenes directly through AI prompts. Control objects, materials, lighting, and execute Python code in Blender effortlessly. Access assets from Poly Haven and generate AI-driven models using Hyper3D Rodin. This integration enhances creative workflows by combining Blender’s robust tools with Claude’s intelligent guidance, making 3D content creation faster, interactive, and more intuitive. Perfect for artists and developers seeking AI-assisted 3D design within Blender’s environment.
Meta Ads
Remote
Unlock AI-driven insights and control for your Meta ad campaigns across Facebook and Instagram. Meta Ads MCP enables large language models to analyze performance, visualize creatives, and provide strategic recommendations through a unified interface. Manage campaigns, ad sets, and ads with actionable feedback on budget allocation, targeting, and creative improvements. Compatible with any MCP client and supports comprehensive campaign management on all Meta platforms. Leverage automated monitoring, creative optimization, and detailed performance metrics to maximize your advertising impact effortlessly.