Give Your AI a Real Browser.
Agent Browser is a macOS menu bar app that gives AI assistants full control of a real Chromium browser — locally, privately, with no cloud intermediary.
The local browser automation engine for Claude, Cursor, and CrewAI.
Perfect for OpenClaw and Claude AI. Stress-tested by Claude in April 2026: 9.5/10 →
Or get it free: Agent Browser is included when you buy Agent Mac (£44.99). See pricing →
You (in Claude) → MCP tools → Agent Browser → ChromiummacOS 14 Sonoma or later · 90 MB download

Your AI Can Read the Web. Now It Can Use It.
Agent Browser runs a local automation engine that exposes 37 powerful MCP tools to any connected AI agent. Ask Claude to research a topic, fill out a form, log into a site, or extract clean content from a page — it handles the browser directly while you stay in the conversation.
Here’s What Claude Had to Say About Agent Browser
In April 2026, we asked Claude to stress test Agent Browser. It ran 100+ operations across 10+ domains — navigation, JS execution, multi-tab orchestration, session persistence, even an infinite loop — with zero crashes.
“It’s a genuinely production-ready browser automation platform.” — Claude Sonnet 4.6
Read the Full Stress Test TranscriptPerfect for OpenClaw and Claude AI users. Connects over MCP, with one-click setup for Claude Desktop, Claude Code and Cursor.
Why Agent Browser
Full Programmatic Multi-Tab Control
The first AI agent browser with automatic tab registration, provenance tracking, and agent-callable tab switching via MCP. Your AI knows which tab spawned which — and can navigate between them on demand.
Native Mac Menu Bar AI Browser
The first native Mac menu bar app that packages a full AI agent browser — with GUI, session management, and MCP — in one app. No terminal, no config files, no Docker: one click in Setup downloads the automation browser (Chromium) on first run.
Works With What You Already Use
One click for Claude Desktop, Claude Code and Cursor, with no manual JSON editing. You can add other MCP clients by hand over stdio. CrewAI and scripts use the local HTTP API.
Claude Desktop
one click · MCP stdio
Claude Code
one click · MCP stdio
Cursor
one click · MCP stdio
OpenClaw
manual setup
CrewAI
via local HTTP API
Everything Your AI Needs to Control the Web
Not a scraper. A real browser engine your AI drives step by step, and can check that each step landed.
Dual-Mode Operation
Fast headless Chromium by default, and you can show or hide its window with one call. For sites that want a genuine Chrome, turn on "Use your real Chrome" in Settings (needs Google Chrome installed). It runs a separate profile seeded with a copy of your Chrome cookies, and takes effect after you restart the engine.
Session Persistence
Save and restore cookies and localStorage by name. Your AI stays authenticated across conversations — tested with 169 cookies, 3 origins.
Multi-Tab Awareness
Open, track, and switch between tabs. Full provenance tracking shows which tab spawned which — agents never lose context.
Clean Content Extraction
Fetch any URL as clean markdown, with up to 67% fewer tokens than raw HTML. Extraction runs on your Mac with no API key. Developers can opt in to the Firecrawl cloud service as a fallback for near-empty pages by setting their own key.
Host-Based Execution
Runs on your actual machine — real network access, real browser fingerprints, and access to sites that block sandboxed cloud browsers.
Real-Time Dashboard
Live run monitor at localhost:3210 with action logs, screenshots, and status. See every step your AI takes and why.
ARIA-Mode Snapshots
Token-efficient accessibility tree snapshots help agents find the right elements without processing full HTML.
Local & Private
Your sessions, saved logins, screenshots and run history stay on your Mac, and its services listen only on 127.0.0.1. No cloud browser in the middle: sites see a normal browser on your Mac. Its own calls out are the update check, the licence check and Setup downloads, plus any AI or Firecrawl service you add a key for.
Error Resilience
Invalid or blocked URLs, DNS failures, bad selectors, hidden or covered elements and slow pages come back as structured errors, most with a typed code and a recovery hint, so your AI knows what to do next.
37 MCP Tools. Total Browser Control.
Navigate, click, type, fill, scroll, hover, select, press, wait, screenshot, snapshot, extract, session save/restore, and multi-tab management.
navigateGo to any URL, with HTTP status reporting.
openNavigate, wait for the page to settle and return clickable refs — in one call.
actClick, type, fill, hover, scroll, press — batched and verified.
get_locationCheap orientation: current URL and title (~20 tokens).
wait_for_settledWait for the page to quiesce before reading or acting.
read_networkInspect captured requests — see the 401/redirect behind a failure.
read_consoleRead console output and uncaught JS errors.
set_budgetDaemon-enforced action and time budget that stops runaway loops.
check_backpressureDetect rate-limit and anti-bot signals before continuing.
set_safe_modeConfirm-gate irreversible actions for unattended runs.
confirm_actionApprove and execute an action that safe mode gated.
plan_checkpointPersist and resume a multi-step plan across restarts.
idempotency_guardNever re-run an irreversible step after a resume.
site_memoryPer-domain learned site facts, so the agent stops re-discovering each site.
downloadCapture a file download to disk, with sha256.
set_dialog_policyAuto-handle native alert / confirm / prompt dialogs.
scroll_untilExhaust infinite feeds until a stop condition is met.
fill_formFill many fields and verify each one stuck.
macroRecord and replay a verified, parameterized flow.
vaultLog in from a Keychain credential — the secret never reaches the agent.
snapshotARIA accessibility (or DOM) snapshot, token-efficient.
screenshotCapture the page as an image the AI can actually see.
extract_cleanAny URL as clean markdown — ~67% fewer tokens.
extract_structuredOn-device structured extraction: markdown plus metadata, or typed fields.
detect_blockerSpot login walls, 2FA, CAPTCHA and Cloudflare interstitials.
page_reportOne-call diagnosis of why a page isn't working.
request_human_assistHand control to the human for 2FA/CAPTCHA, then resume.
resume_human_assistSignal the human has finished, unblocking the run.
get_stateIs the daemon up? Visible or headless, current URL and active guards.
list_runsFull audit trail of recent operations.
watchWatch a page on a schedule and get a Mac notification when it changes.
toggle_windowSwitch between headless and visible mode.
get_formsScan the page for inputs, selects and textareas.
sessionSave, restore or import a logged-in session so you sign in once.
list_tabsList all open tabs with provenance.
switch_tabSwitch tabs by ID. Your own tabs need your OK first.
close_tabClose a tab by ID. Your own tabs need your OK first.
Benchmarked Performance
Headless mode. Real numbers.
Avg navigation
across 10 diverse sites
Fastest nav
cached endpoints
Tokens to orient
get_location instead of a full snapshot
8 tabs parallel
opened simultaneously
90-item scrape
3 pages paginated
Selectors
strategies passing
How It Works
Four steps to browser automation.
Install & Start
On first run, the Welcome Tour (or Settings → Setup → Install Missing) downloads the automation browser, a private copy of Chromium. Then Start All launches all three services: MCP server, browser engine and dashboard.
Auto-Connect
In Settings, Connect AI clients… registers Agent Browser with Claude Desktop, Claude Code and Cursor (whichever you have) in one click, with no manual JSON editing. Restart the client to pick it up.
AI Takes Control
Claude calls tools like navigate, snapshot, and act to control the browser directly.
Watch Everything
Screenshots, action logs, and results are stored locally and viewable in the real-time dashboard.
Built For You
Power Users
Want Claude to handle web tasks — research, form submissions, price tracking, content extraction — without copy-pasting between windows.
Developers
Building AI agents that need reliable browser automation through a clean MCP interface.
CrewAI Users
Connecting multi-agent pipelines to a live browser via HTTP for complex web workflows.
Cursor Users
Want your AI coding assistant to navigate docs, search issues, and read web content inline.
Technical Specs
System Requirements
Ready to Give Your AI a Real Browser?
Everything runs on your Mac. No credentials sent to the cloud. Sessions persist between conversations.
21-day free trial — no signup, no credit card.
macOS 14 Sonoma or later · 90 MB download