Safari MCP: Native Browser Automation for AI Agents on macOS
Safari MCP is an open-source tool under the MIT license that lets an AI assistant operate Safari on your Mac without starting a separate Chrome session. It includes browser actions for navigation, forms, screenshots, network inspection, and more. It works with your existing Safari profile and connects to AI assistants that support MCP, the shared standard used to expose tools to an assistant.
Many browser-automation tools use Chromium or start a separate browser profile. On a Mac, that can mean another browser process and a session with none of your existing Safari logins.
Safari MCP takes a different approach: it just uses the browser you already have open.
Want a quick answer for your business?
Choose your business and what you need to see a recommendation — no form or contact details required.
Table reservations, a digital menu, takeaway orders and arrival reminders — without leaving the kitchen to answer the phone. Explore the solution for your business
Appointment scheduling, automatic reminders and a waiting list that fills cancelled slots. Explore the solution for your business
Appointment scheduling and reminders. Among our clients, reminders reduced cancellations by about 50%. Explore the solution for your business
Automatic lead qualification, property details and tour scheduling — before you have time to reply. Explore the solution for your business
Handle enquiries 24/7, schedule meetings and send documents, with a clear record of every enquiry. Explore the solution for your business
Abandoned cart recovery and order updates. About 70% of online shopping carts are abandoned. Explore the solution for your business
Basic botAround ₪3,500 one-time
Answers recurring questions, sends prices and information, and hands over to a person when needed.
Business packageAround ₪6,500 one-time
Connects to your calendar and CRM, books appointments and can accept payments.
Full AI solutionUp to ₪12,000 one-time
Understands natural language and holds a conversation, connected to several systems at once.
Monthly costs are the same across package levels and depend on the technical route: ₪100–300 for the economical route (typically ₪150), or ₪315–890 for the official Meta API route. Full details in the pricing guide
July 2026 Update — Apple Just Shipped Its Own Safari MCP Server
On July 1, 2026, Apple released Safari Technology Preview 247 with an official, built-in MCP server — announced on the WebKit blog. If you searched “Safari MCP” and landed here, here’s how the two relate:
- Apple’s Safari MCP server is aimed at web developers debugging their own sites: it gives agents access to the DOM, network requests, screenshots, and console output so they can find Safari compatibility issues, analyze performance, and check accessibility. It runs locally, makes no network calls of its own, and currently ships only in Safari Technology Preview — Apple’s separate developer build — not in the Safari you use every day.
- The open-source Safari MCP covered in this article is aimed at automation: 80 tools that drive your real, everyday Safari — the one with your logins and sessions — to fill forms, manage tabs, extract data, and run multi-step workflows.
The two are complementary: Apple’s server inspects pages; this one operates the browser. And Apple building MCP support directly into Safari is the strongest validation yet of the approach this project bet on in early 2026 — native Safari access for AI agents, no Chrome required.
Q2 2026 Update — What Changed for Browser Automation in 2026
Three things changed in the second quarter of 2026 that make this tool even more useful now than it was when it first came out:
Read the section
- Model choice now matters more — Browser agents often make repeated model calls as they inspect a page and choose the next action. Current input, output, and tool-use prices should be checked on the primary Anthropic pricing page and OpenAI API pricing page before estimating a workflow.
- Browsers started building in AI (early 2026) — Chrome added an “AI Assistant” panel powered by Gemini, and Edge now has Copilot built right in. But here’s the catch: those built-in helpers still need a separate AI assistant on your own computer to actually click and type on the page for them. Safari MCP is exactly that piece — and it does the work inside your own logged-in Safari, so your cookies, sign-ins, and extensions all stay put. That fits neatly with how people using Comet, Atlas, and Edge’s AI features already work.
- The wider toolkit grew up (Q2 2026) — There are now supported MCP tools from companies such as Anthropic, GitHub, and Cloudflare. n8n also added memory features for AI agents; check the n8n release notes for the version you run. Together, these pieces can support workflows that browse, retain relevant context, and act later, but setup depends on the sites, permissions, and safeguards involved.
Bottom line: In 2026, AI assistants really do click around real websites for you — and on a Mac, the cheapest way to let them do that is to use the browser you already know and trust. Safari MCP is built for exactly that.
What is MCP?
“MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications.” — Anthropic, Introducing the Model Context Protocol
Read the section
Model Context Protocol, or MCP, is a shared standard for letting AI assistants use outside tools. Think of it like a standard plug and socket: any AI assistant that “speaks” MCP can plug into any tool that also speaks it, and use whatever that tool can do. So when your AI coding helper needs to open a web page, fill in a form, or grab a screenshot, it hands that request to a tool like this one. The tool does the job and passes the result back. If AI assistants are new to you, we wrote a practical guide to AI agents for small business that explains what they actually do and how to set one up.
“Safari uses WebKit, the open source web rendering engine that Apple developed and uses across its operating systems.” — Apple Safari Developer page
Most tools of this kind control Chrome, either through a built-in back channel Chrome offers (its “DevTools Protocol”) or through Playwright. Safari MCP works differently: it controls Safari itself using AppleScript — the simple automation language that already comes with every Mac — helped by a small program that stays running quietly in the background so it’s always ready to respond.
Why Safari Instead of Chrome?
“Safari delivers up to 60% faster JavaScript performance than Chrome on Apple Silicon, while using significantly less memory and power.” — Apple, “Safari is faster”
Read the section
“AppleScript is a scripting language created by Apple Inc. that facilitates automated control over scriptable applications on the macOS operating system.” — Apple Developer, AppleScript Overview
The practical differences matter for daily use:
Performance
Commands are routed through a persistent local helper, so the tool does not need to start a new browser for every action. Actual speed and resource use depend on the Mac, the page, and the connected AI model. Apple describes Safari as optimized for performance and power efficiency on its own hardware; the primary Safari product page contains Apple’s current comparison methodology.
Your Real Browser
Chrome-based tools open a brand-new, empty browser every time — no accounts, no saved sign-ins, nothing. Every task starts from a blank slate, as if you’d never logged in anywhere.
Safari MCP uses your actual Safari — Gmail, GitHub, Slack, Ahrefs, whatever you’re already signed in to. Your AI assistant browses as you, staying logged in to everything you are.
No Focus Stealing
With the Chrome-based tools, every single action yanks the window in front of you. You’re typing away in your editor and Chrome suddenly pops up and grabs your attention. It’s a well-known annoyance for people using AI browser tools.
Safari MCP does all its work out of sight. Safari stays where it is and never jumps in front of you unless you ask it to.
Safari MCP at a Glance
The useful distinction is architectural: it controls the Safari session already on the Mac instead of creating a separate Chromium profile.
Read the section
- Ready-made browser actions: 80 — things like moving between pages, filling forms, taking screenshots, watching network activity, saving data, and checking accessibility
- Resource use: depends on the page, the Mac, and whether another browser would otherwise be running
- Command speed: depends on the page and on the AI assistant’s decision loop, not only on the local helper
- Browser coverage: good for Safari workflows; use a cross-browser tool when the task must also be verified in Chrome, Firefox, or Edge
- Focus behavior: designed to operate Safari without deliberately bringing it to the foreground
- AI cost: determined by the connected model and the number of steps in the workflow
- Software license: MIT; connected models and services have separate terms
- What setup takes: one small block of settings plus flipping 2 switches on your Mac, and it works across 5 supported AI assistants
Quick Setup
To connect Safari MCP, you paste a small block of settings into your AI assistant — this is what tells it the tool exists and how to start it. Copy the lines below into your assistant’s settings file (don’t worry about understanding each line; it just names the tool and how to run it):
👨💻 Show the code (for developers)
{
"mcpServers": {
"safari": {
"command": "npx",
"args": ["-y", "safari-mcp"]
}
}
}Or, if you’d rather skip the copy-paste, use the one-click install buttons for VS Code and Cursor.
The last step is to give Safari and your editor permission to work together. It’s two quick toggles:
- In Safari, open the Develop menu and turn on “Allow JavaScript from Apple Events” (this lets other apps run small commands on the page)
- In System Settings, allow your editor to control (“Automate”) Safari
That’s it. Your AI assistant can now browse in Safari.
What Can It Do? (80 Tools)
The tool comes with 80 actions, grouped into these kinds:
Read the section
Navigation & Tabs — Open web addresses, work with tabs, go back and forward, and refresh. Tabs are handled safely: the AI keeps track of the tabs it opened itself and never disturbs the ones you’re using.
Page Interaction — Click things, fill in forms, type, hover, drag, and scroll. It can even click the way a real person would, which some sites insist on before they’ll respond.
Data Extraction — Pull information off a page: the text, the links, tables, images, and behind-the-scenes details. It can also read how a page is styled and lay out its structure in a tidy form the AI can work with.
Screenshots & Visual — Take a picture of the whole page or just one part of it. It can also pretend to be a phone or tablet so you can check how a page looks on smaller screens.
Network & Performance — Watch what a page quietly loads in the background, feed it fake responses for testing, slow the connection down on purpose, and measure how fast the page loads.
Storage & State — Read and change the little bits of data a site saves on your machine to remember you (cookies and the like), and save or reload a snapshot of all of it.
Accessibility — Lay out the whole page the way a screen reader would see it, so you can check that your site works for people with disabilities and meets WCAG, the web’s accessibility standard.
Framework Support
Today’s websites are usually built with tools like React, Vue, and Angular, and they have a quirk: they don’t trust text that just appears in a field on its own. If a tool quietly drops text into a box, the site often doesn’t notice, so the form ends up looking empty. Safari MCP knows how to talk to each of these tools in the way it expects, so the text actually registers:
Read the section
- React — Gently resets what React is watching for, so it accepts the text as if a person had typed it
- Vue.js — Sends Vue the exact signal it’s listening for so it picks up the change
- Angular — Sends both of the signals Angular needs before it will accept what was entered
- ProseMirror / Draft.js / Slate / Lexical — For the fancier text boxes (the kind where you can make text bold or add links), which ignore text that isn’t typed by a real person, it uses the same copy-and-paste your keyboard would. Our deep-dive on why these tools quietly fail on rich-text boxes explains the safety rule that trips up automation on LinkedIn, Notion, and Google Docs.
- Shadow DOM — Reaches into the sealed-off parts of a page that live inside self-contained building blocks — spots that most tools simply can’t get to
Safari MCP vs Playwright vs Chrome DevTools MCP
Read the section
Scroll sideways to see all columns.
| Feature | Safari MCP | Playwright | Chrome DevTools MCP |
|---|---|---|---|
| Browser engine | Native WebKit (Safari) | Chromium/Firefox/WebKit | Chromium |
| CPU usage on Apple Silicon | Measure on the target workflow | Measure on the target workflow | Measure on the target workflow |
| Real user sessions (cookies/logins) | ✅ Yes — your actual Safari | ❌ Fresh profile | ❌ Fresh profile |
| Focus behavior | Designed for background operation; verify each command | Depends on browser mode and test setup | Depends on the debugging session |
| Command path | Persistent local helper | Browser automation process | Chrome debugging connection |
| Setup complexity | One JSON line + 2 toggles | npm install + browsers | Chrome flags + DevTools |
| License | MIT (open-source) | Apache 2.0 (Microsoft) | MIT (Google) |
| Tool catalog | Check the installed Safari MCP version | Check the installed Playwright version | Check the installed Chrome DevTools MCP version |
| Lighthouse audits | ❌ Not supported | ⚠️ Via API | ✅ Native |
| Cross-browser testing | ❌ Safari only | ✅ Chrome/Firefox/WebKit | ❌ Chrome only |
| Rich-text editors (Lexical/ProseMirror) | Editor-specific paths are available; test the target app | Behavior depends on editor and fill method | Behavior depends on editor and command path |
| Shadow DOM access | Test open and closed roots on the target page | Test the target component | Test the target component |
| Network mocking | ✅ Yes | ✅ Yes | ✅ Yes |
| Best for | Daily AI agent browsing on macOS | Cross-browser CI/CD | Chrome perf diagnostics |
When to Use Chrome Instead
Safari MCP is a good fit when the task belongs in Safari. Chrome DevTools or a cross-browser tool is the better pick for these jobs:
Read the section
- Lighthouse audits — a page-quality report card that only Chrome can produce
- Chrome’s own diagnostic tools — deep reports on speed, memory use, and which parts of a page’s code actually get used
- Testing across browsers — when you specifically need to see how a page behaves in Chrome
The two tools work well side by side. Reach for Safari MCP for your everyday browsing and testing, and switch to the Chrome DevTools tool when you need those Chrome-only checks. For a broader look at how we use automation in production, see our business automation guide, our n8n self-hosted setup guide for the orchestration layer, and our deep-dive on MCP browser automation for rich text editors. For comparing automation platforms see n8n vs Make vs Zapier. For the strategic framing of where browser-driving AI fits in a small-business stack overall, see our AI in business overview.
Open Source
Safari MCP is MIT licensed and fully open — anyone can read the code, and it’s about as free-to-use as software gets. The whole thing is just two files: safari.js, which does the actual browser work, and index.js, which lets the AI talk to it.
It’s currently sitting at 28 GitHub stars and 2,000+ downloads a month, and other people have pitched in too — sending fixes, improvements, and teaming up with folks building similar Mac tools.
Links:
A WhatsApp bot can run defined replies, appointment steps and lead capture outside office hours, subject to connected-system availability. Projects start from $1,000 one-time. Tell me about your business →
Get a Custom QuotePrefer to chat? WhatsApp me · full pricing · our projects
Ready to automate your business?
50+ automation projects completed. Tell me about yours — I'll show you exactly what we can automate.
Get a Custom QuoteI’ll reply as soon as I can · Project quote based on scope