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.

Back to Blog

You Do Not Need an MCP Server for Every Mac App - Accessibility APIs as a Universal Interface

Fazm Team·March 14, 2026·3 min read

mcpaccessibility-apimacosarchitecturedeveloper-tools

You Do Not Need an MCP Server for Every Mac App

The Model Context Protocol is great for connecting AI agents to external services. But when it comes to controlling native Mac apps, there is a simpler approach that most people overlook.

Instead of building a separate MCP server for Mail, another for Calendar, another for Finder, and another for every other app you want your agent to use - just use the macOS accessibility API. One interface, every app.

The MCP Per-App Problem

The typical setup for an AI agent that controls Mac apps looks like this:

MCP server for browser automation
MCP server for file system operations
MCP server for email
MCP server for calendar
Custom MCP server for each additional app

Each one needs to be built, configured, maintained, and kept in sync. Managing 10+ MCP servers is genuinely painful. Configuration files, version mismatches, servers that crash silently.

The Accessibility API Alternative

Every well-built Mac app exposes its UI through the accessibility framework. This is the same interface that screen readers like VoiceOver use. It gives you:

Read any element on screen - buttons, text fields, menus, labels
Perform actions - click, type, select, scroll
Navigate the UI hierarchy - find elements by role, label, or position
Works across all apps - one API, not one-per-app

An AI agent that speaks the accessibility API can control Mail, Calendar, Finder, Safari, Terminal, Xcode, Slack, and any other app without a single line of app-specific integration code.

How to Explore It

The Accessibility Inspector is built into Xcode and most people do not even know it exists. Open it from Xcode > Open Developer Tool > Accessibility Inspector. Point it at any app and you can see the entire UI tree - every element, every label, every available action.

This is the best free macOS automation tool nobody talks about. Before building an MCP server for a specific app, open the Accessibility Inspector and see if the app already exposes everything you need through the accessibility tree. It usually does.

When You Still Need MCP

Accessibility APIs are for UI-level interaction. If you need:

API-level data access (reading a database, querying an API)
Background processing (running without a visible window)
Cross-machine operations (controlling a remote server)

Then MCP is the right tool. The sweet spot is using accessibility APIs for local app control and MCP for everything else.

Fazm uses accessibility APIs as its primary interface for controlling macOS apps. Open source on GitHub. Discussed in r/ClaudeAI.

You Do Not Need an MCP Server for Every Mac App - Accessibility APIs as a Universal Interface

You Do Not Need an MCP Server for Every Mac App

The MCP Per-App Problem

The Accessibility API Alternative

How to Explore It

When You Still Need MCP

Related Posts

Using Claude as an Execution Layer - Markdown Specs, MCP Tools, No Traditional Code

What We Learned Building a macOS AI Agent in Swift (ScreenCaptureKit, Accessibility APIs, Async Pipelines)

Building a macOS Desktop Agent with Claude - How AI Wrote Most of Its Own Code