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

Why Removing Unused MCP Servers Speeds Up Claude Code More Than Removing Skills

Fazm Team·March 17, 2026·3 min read

claude-codemcpperformancedeveloper-toolsoptimization

Why Removing Unused MCP Servers Speeds Up Claude Code

If Claude Code feels slow to start up or sluggish during sessions, the first thing to check is how many MCP servers you have configured. Trimming unused ones made way more of a difference for us than removing skills.

The reason is simple: MCP servers are actual processes and they all have to handshake on startup.

Skills vs MCP Servers

Skills are essentially prompt templates with some metadata. Loading a skill means reading a markdown file and adding it to the context. This is fast - a few milliseconds per skill, and they only consume tokens in the context window.

MCP servers are different. Each one is a separate process that Claude Code spawns and maintains:

Process startup. Each MCP server launches as its own process (Node.js, Python, or whatever runtime it uses).
Handshake. Claude Code sends an initialize request and waits for the server to respond with its capabilities.
Tool registration. The server reports all its available tools, which get added to Claude's context.
Keepalive. The process stays running for the duration of the session, consuming memory.

With 15 MCP servers configured, startup involves spawning 15 processes and completing 15 handshakes. If any server is slow to initialize (common with servers that need to authenticate with external services), it blocks the entire startup sequence.

The Practical Impact

We went from 12 configured MCP servers down to 4 that we actually use regularly. The result:

Startup time dropped from 8-12 seconds to 2-3 seconds.
Context window usage decreased because fewer tool definitions were being injected.
Session stability improved because fewer background processes meant fewer random crashes.

What to Keep

Keep the MCP servers you use daily. For everything else, remove them from your configuration and add them back when you need them. The 30 seconds it takes to re-add a server config is less than the cumulative startup delay of keeping it loaded for every session.

The same principle applies to Fazm - we keep the MCP server count minimal and focused on the tools the agent actually needs for the current task.

Why Removing Unused MCP Servers Speeds Up Claude Code More Than Removing Skills

Why Removing Unused MCP Servers Speeds Up Claude Code

Skills vs MCP Servers

The Practical Impact

What to Keep

More on This Topic

Related Posts

I Installed 20 MCP Servers and Everything Got Worse - Why Fewer Is Better

Skills vs MCP vs Plugins - What's the Difference?

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