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

Building an MCP Server That Combines macOS Accessibility APIs With Screen Capture

Fazm Team·March 17, 2026·2 min read

mcpaccessibility-apiscreen-capturemacosswift

Building an MCP Server for macOS Accessibility and Screen Capture

The biggest unlock for building Fazm was creating an MCP server that wraps macOS accessibility APIs together with screen capture. The AI can literally see what is on screen and click things.

This is the bridge between "AI that talks about your computer" and "AI that uses your computer."

Why Both APIs Together

Accessibility APIs alone give you structured data - element names, types, positions, hierarchy. But they miss visual context. An accessibility tree tells you there is a button labeled "Submit" but does not tell you it is grayed out, partially hidden behind a modal, or surrounded by a red error border.

Screen capture alone gives you visual context but no structure. A screenshot shows you exactly what the screen looks like, but the AI has to use vision models to figure out what is clickable and where.

Combining them gives the agent the best of both:

Structure from accessibility. The agent knows every interactive element, its type, label, and position.
Visual context from screen capture. The agent can verify what it sees matches what the accessibility tree reports.
Confidence scoring. When the accessibility tree says a button is at position (200, 300) and the screenshot confirms a button is visually present at that location, the agent can act with high confidence.

The MCP Architecture

The MCP server is written in Swift (because the macOS accessibility and screen capture APIs are native frameworks) and exposes tools like:

get_accessibility_tree(app: String) - returns the full UI element hierarchy for an app
capture_screen(region: Rect?) - captures a screenshot of the full screen or a specific region
click_element(app: String, element: String) - clicks a specific element by its accessibility identifier
type_text(text: String) - types text into the currently focused field

The Key Insight

Neither API alone is sufficient for reliable desktop automation. Accessibility APIs miss visual state. Screenshots miss semantic structure. The combination is what makes the agent actually reliable.

Building an MCP Server That Combines macOS Accessibility APIs With Screen Capture

Building an MCP Server for macOS Accessibility and Screen Capture

Why Both APIs Together

The MCP Architecture

The Key Insight

More on This Topic

Related Posts

Giving Claude Code Eyes and Hands with macOS Accessibility APIs

MCP Servers That See Your Screen vs Ones That Read Your Clipboard

Open Source MCP Server for macOS Accessibility Tree Control