How much time will I actually save with Fazm?

Most users report saving 45-90 minutes per day on repetitive tasks. The biggest time savings come from email management (drafting replies, sorting, archiving), form filling (expense reports, CRM updates, applications), research (comparing products, gathering data from multiple sites), and social media (cross-posting, scheduling, replying). For example, booking a flight that normally takes 10 minutes of clicking through airline sites takes a single voice command with Fazm. Filing an expense report that requires opening a PDF, extracting numbers, and entering them into a spreadsheet becomes one spoken sentence. The more repetitive and multi-step your daily work is, the more time you get back.

What exactly can Fazm control?

Fazm controls everything you can do manually on your Mac. That includes mouse movements and clicks, keyboard typing, browser navigation and form filling, app switching, file management in Finder, and system-level actions. It uses direct browser DOM control for web interactions - meaning it reads and manipulates the actual page structure rather than taking screenshots and guessing where to click. For native macOS apps, Fazm uses accessibility APIs to interact with buttons, menus, text fields, and other UI elements. This works across any application: Chrome, Safari, VS Code, Slack, Figma, Terminal, Mail, Calendar, and more.

How is Fazm different from ChatGPT or Claude?

Chatbots like ChatGPT and Claude give you answers in a conversation window. Fazm takes action directly on your computer. When you say 'reply to Sarah's email,' Fazm opens your email app, finds Sarah's message, writes a contextual reply, and sends it. A chatbot would tell you what to write, but you still have to do all the clicking and typing yourself. Fazm moves your mouse, types on your keyboard, clicks buttons, and navigates between apps. It is a computer agent, not a chat assistant.

How does the memory layer work?

Fazm builds a personal knowledge graph by extracting information from your files, browsing history, conversations, and daily activity. Over time, it learns your contacts (names, emails, relationships), accounts and credentials, preferences (formatting, tone, scheduling habits), and frequently used workflows. In your first week, you might say 'Reply to Sarah's email, she's my cofounder, her email is sarah@acme.com.' By week four, you just say 'Reply to Sarah' because Fazm already knows who she is. By week eight, Fazm can draft the reply before you even ask. All of this data stays locally on your Mac - your knowledge graph never leaves your machine or gets sent to any cloud service.

Is Fazm safe? Can it mess up my computer?

Safety is built into every layer of Fazm. You watch every action in real-time on your screen - Fazm moves your mouse and types visibly, so there is nothing hidden. You can stop any action at any point by pressing a keyboard shortcut. Fazm also shows you what it plans to do before executing destructive actions like deleting files or sending emails, giving you a chance to confirm or cancel. Because Fazm is open source, the code is fully auditable on GitHub. There is no hidden behavior, no background processes making changes you cannot see, and no actions that bypass your screen.

What platforms does Fazm support?

Fazm currently supports macOS, running natively on both Apple Silicon (M1, M2, M3, M4) and Intel Macs. It is built with Swift and uses macOS-specific frameworks like ScreenCaptureKit for screen analysis and Accessibility APIs for app control, which is why macOS is the primary platform. Windows and Linux support are on the roadmap but do not have release dates yet. You can also control your Mac remotely from your phone using Fazm Remote, which gives you voice access to your desktop while you are away from your computer.

How does Fazm voice input work?

One keyboard shortcut activates push-to-talk. Hold the key, speak naturally about what you need done, and release. Fazm transcribes your speech locally using on-device models, so there is no network latency for the voice recognition step. You do not need wake words like 'Hey Siri' or 'OK Google' - just press and talk. You can also type commands into the floating toolbar if you prefer text input. Fazm understands natural language, so you do not need to memorize specific commands. Say 'book me a flight to Tokyo next Thursday' or 'find the cheapest AirPods on Amazon' and Fazm figures out the steps.

Is my data sent to the cloud?

Fazm processes screen analysis and memory entirely on your machine. The personal knowledge graph, file indexing, and screen capture all run locally. The only data that leaves your Mac is the intent - a text description of what you want to accomplish, which is sent to the AI model (Claude or GPT) for action planning. Your actual screen content, file contents, browsing history, and personal knowledge graph never leave your computer. Fazm is also open source, so you can verify exactly what data is transmitted by reading the code on GitHub. For users who need complete air-gapped operation, local model support is planned.

Is MCP Dead? No - 10 MCP Servers Solve Problems CLI Cannot

Fazm Team·March 17, 2026·3 min read

mcp mcp-servers cli accessibility-api macos desktop-automation

Is MCP Dead? No - 10 MCP Servers Solve Problems CLI Cannot

Every few weeks someone declares MCP dead. "Just use CLI tools." "It is overengineered." "Nobody needs it." Meanwhile, people running 10 MCP servers daily know they solve a fundamentally different problem than command-line tools.

What CLI Cannot Do

Try getting the macOS accessibility tree without MCP. You need an MCP server that connects to the Accessibility API, traverses the UI hierarchy, and returns structured data about every element on screen - buttons, text fields, labels, their positions, their states.

There is no curl command for that. No jq filter that gives you the contents of a Figma canvas. No shell script that reads the state of a running Electron app's internal components.

MCP servers bridge the gap between what an LLM can orchestrate and what the operating system exposes. They are the connective tissue between AI agents and native platform capabilities.

The 10 Server Setup

A practical daily setup might include:

macOS Accessibility - reading and interacting with any app's UI
Playwright - browser automation with full DOM access
File System - structured file operations with permissions
Git - repository operations beyond what the CLI exposes
Database - direct query access without connection string juggling
Calendar/Email - Google Workspace integration
Memory/Knowledge - persistent agent memory across sessions

Each server exposes capabilities that do not have a clean CLI equivalent. The accessibility tree alone justifies the MCP architecture - there is simply no other way to give an LLM structured access to what is on your screen.

The Real Criticism

The valid criticism of MCP is not that it is unnecessary - it is that the ecosystem has too many low-quality servers that wrap simple API calls that could be a curl command. An MCP server that wraps a REST API is pointless. An MCP server that gives you access to the macOS accessibility tree is essential.

MCP's Future

MCP's value increases as agents move from chat to action. The more an agent needs to interact with native apps, hardware, and OS-level features, the more it needs MCP servers as its interface layer. CLI tools are great for text-in, text-out operations. MCP servers handle everything else.

Fazm is an open source macOS AI agent. Open source on GitHub.

Is MCP Dead? No - 10 MCP Servers Solve Problems CLI Cannot

Is MCP Dead? No - 10 MCP Servers Solve Problems CLI Cannot

What CLI Cannot Do

The 10 Server Setup

The Real Criticism

MCP's Future

More on This Topic

Related Posts

Giving Claude Code Eyes and Hands with macOS Accessibility APIs

Building an MCP Server for Native macOS App UI Control

How an MCP Server Lets Claude Control Any Mac App