Browser Automation MCP Servers for OpenAI Agents SDK

MCP server to drive and inspect a running Next.js app: headless route/error introspection + a real-event in-page browser bridge (click

Screenshot API for MCP clients. Capture any URL as PNG with mockup mode support.

Playwright Tools for MCP

Give any MCP client the ability to browse and interact with the web via WebUplink.

Local Playwright browser through residential proxies — agent picks country + sticky identity

Minimal, auth-secured MCP server for real browser access

Personal-use MCP server that searches Coupang through YOUR OWN Chrome browser (CDP). No API key needed. Not affiliated with Coupang.

Add inline, range-anchored comments to Google Docs - the one comment op the Google APIs can't do.

Screenshots, PDFs, video, markdown and page data from any website, via Urlbox.

Gemini Computer Use is an MCP server that runs on your own machine, started by your client over stdio.

MCP server and Firefox add-on that let an AI agent drive your real, logged-in browser. Free tier.

Capture screenshots, detect visual regressions between page versions, and analyze with AI.

Isolated browsers with a persistent identity for AI agents, on your own Windows machine.

Local-only Chrome and Edge control for MCP clients through an origin-scoped extension.

Browse the web and run Google search through real Singapore mobile carrier IPs.

Automate a real, logged-in browser on your own device — no stored credentials, no bot detection.

Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.

MCP server for Google AI Search Mode with CAPTCHA handling. Free, token-efficient web research with source citations.

MCP server combining NSTBrowser profile management with Playwright browser automation via CDP

Control specific, already-open account-isolated Personae browser identities with MCP.

Minimal network monitoring MCP tool for Playwright browser automation