Browser Automation MCP Servers for OpenAI Agents SDK

MCP server bridging Playwriter's Chrome extension with Playwright-style structured tools for VisionClaw

Detection-resistant browser automation aimed at safely driving real browsers.

ReverseCraft DevTools MCP - MCP server for browser debugging and reverse engineering

MCP server for Safari browser control and debugging on macOS

Screenshot, diff, audit and sitemap-capture any web page — 5 MCP tools for AI agents.

Capture web pages as screenshots (returned inline) or PDFs via the Screenshotty API.

Jarvis MCP – Browser-based voice input/output for AI Assistant conversations via MCP (Model Context Protocol)

Screenshot API for AI agents: capture any public URL as JPEG, PNG, WebP, AVIF, or PDF.

Screenshots, PDFs and Markdown from any URL or HTML for AI agents, via the SnapForge API

MCP server that exposes Stagehand browser automation capabilities

Token-first headless browser for AIs. Extracts a tiny semantic graph, cutting HTML bloat by 95%.

MCP server for SurfAgent — gives AI agents a real managed Chrome browser via CDP. Navigate, click, type, screenshot, manage tabs, inspect

Tabrix Native-Messaging host (Node)

TigerHill MCP tools for Playwright automation

WebRendererMCP renders HTML using Playwright and exposes it as an MCP server.

MCP server for web scraping, page rendering, and content extraction — renders any URL (including SPAs) with Playwright, extracts readable

MCP server for remote browser automation using BrowserCat

MCP Server for Chrome browser automation via debugging protocol with session persistence

MCP server for Chrome DevTools Protocol integration - control Chrome tabs, execute JavaScript, capture screenshots, and monitor network

A concurrent browser MCP server that supports multiple parallel browser instances

MCP server for browser console logs