— · MIT
🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
v0.4.15 · BSD-3-Clause
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
v2.9.4 · MIT
A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.
v0.9.36 · MIT
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copilot. Test Flutter, React Native, iOS, Android, Web, Electron, Tauri, KMP, .NET MAUI — all from natural language.
v1.7.0 · Apache-2.0
MCP server for Google PageSpeed Insights & Chrome UX Report APIs — 17 tools to analyze, compare, and optimize web performance with Claude, Cursor, or any MCP-compatible AI client
v4.0.3 · Apache-2.0
AI Agent-first JS 逆向 MCP Server:有头 Chrome 调试、断点、网络/WebSocket 分析、Patchright 反检测,可选 CloakBrowser。
v1.0.0 · no license
A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches. Local alternative to SERP APIs with MCP server integration.
v0.14.4 · Apache-2.0
MCP server for browser automation via Jan Browser extension - provides tools for web navigation, interaction, and search
v1.0.0 · MIT
Thin WebMCP-to-MCP v2 browser adapter with native Chrome tool mirroring
v2.16.3 · MIT
Safari browser automation for AI agents — native macOS, zero Chrome overhead. 97 tools via AppleScript + JavaScript.
— · AGPL-3.0
Your own search engine
v0.2.2 · MIT
Browser automation MCP server for Claude, powered by Puppeteer.
v0.17.3 · MIT
Let coding agents verify UI changes on real iOS, Android, and web surfaces, then enforce reviewed proof in deterministic CI.
v0.6.0 · MIT
Reliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.
v2.23.0 · MIT
Translate web pages, PDFs and text on your own machine - Chrome's built-in on-device model by default, a local LLM through Ollama when you want one. Browser extension, CLI, and MCP server.
v1.0.4 · MIT
Enables AI agents to run durable, isolated, and observable browser automation tasks via Playwright, with persistent profiles, recovery, evidence capture, and unattended execution for long-running web workflows.
— · MIT
Browse the web, directly from Cursor etc.