browser MCP servers

Build, run, inspect, and publish browser extensions from any MCP client. 34 tools, 13 browsers.

Drive your real, logged-in Chrome from any AI agent - 40 tools. Needs our Chrome extension too.

Native Safari browser automation for AI agents — 98 tools, zero Chrome overhead.

Drive your real Chrome over MCP: real logins and cookies, multi-tab automation, deny-all by default.

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

Control a local headless Chrome browser: open pages, read titles, and take screenshots.

domscout browser API as MCP tools: screenshots, Markdown, structured data, page automation, crawls.

Chrome automation via nodriver: 70 tools, isolated browsers, profiles and configurable startup.

MCP server for creating, running, inspecting, and scheduling Figranium browser automations.

Browser-local and CLI static evidence for deployed AI model artifacts.

Runtime CSS probe — inspect layout, overflow, scroll chains in a real browser. For AI agents.

Search Perplexity using your browser login. Returns answers, sources, and thread URLs. No API key.

Remote Linux boxes for coding agents: Docker, a browser, screenshots, logs, human takeover.

Browser automation MCP for solving captchas with CapMonster Cloud via Patchright.

Record browser bugs - frames, clicks and console logs - and hand them to your AI over MCP.

Arc browser MCP for macOS: agent window, snapshots, DevTools input, guardrails

MyAtriumHealth (Epic MyChart) records via your signed-in browser tab

AWS, GitHub and connected services from your agent, no keys to paste, plus local shell and browser.

Lint rendered pages against a design system in a real browser, across six widths, with the fix.

Fetch your own Delhaize (Belgium) till receipts and weekly promotions with a headless browser.

Let Claude use your Zen Browser, like Claude in Chrome. No extension, only sites you allow.

Create, launch, check and drive Nullprint multi-profile browser profiles from any MCP agent.