Browser Automation MCP Servers for OpenAI Agents SDK

Model Context Protocol server for Anakin (anakin.io) — gives AI agents in Claude Desktop, Cursor, Windsurf, VS Code, and other

Model Context Protocol (MCP) server for controlling Google Chrome browser on macOS. Enables AI assistants like Claude to automate Chrome

Bridge Claude Code with Perplexity Comet for autonomous browsing and tab management

Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.

APIFreaks MCP: live APIs for agents. Enable modules with ENABLE_MODULES; discover via list_modules.

MCP server for the @agentutility retail cluster — pay-per-call x402 tools, no API keys, USDC on…

A Python MCP server for Selenium WebDriver — 85 tools for browser automation, alerts, frames, shadow DOM, cookies, mobile emulation

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

Playwright Tools for MCP with Electron Support

Search Firefox browser extensions on AMO. No key required.

Browser control tool — lets AI agents control the Chrome browser via CLI or MCP protocol

Stealth Chrome MCP server — nodriver + Chromium + 80+ tools with Cloudflare/Turnstile bypass, CapSolver, storage-state reuse

MCP tool for communicating with a Chrome extension via WebSocket

Read and act on Safari — history, tabs and reading list, writes off by default

Browser-measured visual debugging and verification tools for coding agents.

Resumable browser, API and MCP workflows for AI agents. Verify CSV/Excel batches locally.

MCP server that connects to the GoLogin API

Stage1 Inspector — local website capture, evidence views and design comparison

Better Playwright MCP v3 - High-performance browser automation with intelligent content search

MCP server for desktop, browser (CDP), and Android automation. Screenshot, OCR, click, type.

Website screenshots for AI agents: full-page, country proxies, ad & cookie-banner removal