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

MCP Servers That Pipe Raw Data Beat REST API Wrappers

Fazm Team·March 17, 2026·3 min read

mcpcontext-windowraw-dataapi-designagent-tools

Raw Data Wins

Not all MCP servers are created equal. The ones that pipe raw data directly into the LLM's context - full accessibility trees, complete transcripts, unprocessed documents - are dramatically more useful than the ones that wrap a REST API and return structured JSON summaries.

The difference is what the LLM can reason about. When you give it the full accessibility tree of a macOS application, it can see every button, every text field, every label. It can understand the layout, infer relationships between elements, and make decisions about what to interact with. When you give it a pre-processed summary, it can only work with whatever the MCP server developer decided was important.

Why REST Wrappers Fall Short

A typical REST API wrapper MCP server looks like this: the agent calls a tool, the tool makes an HTTP request, parses the response, and returns a subset of fields. The LLM never sees the full response. It cannot ask follow-up questions about data that was filtered out. It is working with someone else's interpretation of what matters.

This creates a bottleneck. The MCP server developer has to anticipate every possible use case and expose the right fields. In practice, they expose the obvious ones and miss the edge cases - which are exactly the cases where you need an AI agent in the first place.

The Raw Data Approach

The best MCP servers are simple pipes. They take raw data from the environment and put it in context:

Accessibility tree traversals - the full tree, not a summary
Meeting transcripts - every word, not a generated summary
Document contents - the complete text, not extracted keywords
Screen state - structured representation of everything visible

The LLM is better at extracting relevant information from raw data than a pre-built parser is at anticipating what information will be relevant.

The Token Tradeoff

The objection is obvious: raw data is expensive. Full accessibility trees can be thousands of tokens. Complete transcripts even more. But this is a tradeoff worth making. The cost of extra tokens is predictable and manageable. The cost of missing information is an agent that fails on edge cases.

Build MCP servers that trust the LLM to handle raw data. The LLM is the smart part of the system - let it do the interpretation.

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

MCP Servers That Pipe Raw Data Beat REST API Wrappers

Raw Data Wins

Why REST Wrappers Fall Short

The Raw Data Approach

The Token Tradeoff

More on This Topic

Related Posts

Why 200K Context Models Outperform 1M When You Aggressively Clear Context

Accessibility Tree Dumps Overflow LLM Context Windows - How to Fix It

The Gap Between Agent Memory and Agent Execution - You Need Both