Drive a web browser.
SceneScout — exploratory UI testing for AI coding agents. An MCP server that gives any agent (Claude Code, Cursor, VS Code Copilot, Codex, Gemini CLI and others) a structured view of a running web app, always-on oracles, a network-level write policy, memo
Hand a browser goal to TypeSafe Jev in your Chrome or a throwaway one; get one checked summary.
Drop-in WSL-safe wrapper for @playwright/mcp. Prevents GPU crashes on Windows Subsystem for Linux by disabling Chromium GPU acceleration through the dxg bridge.
Google PageSpeed Insights and CrUX: six workflow tools for web performance.
MCP server for OpenWeb — the booking-grade reliability layer for AI agents. Self-host with docker-compose for free, OR set OPENWEB_BRAIN_URL + OPENWEB_BRAIN_KEY to point at the hosted brain.
AI-agent skill: build Mosaic Pro (Nextend) WordPress sites by writing the underlying data model directly - 23 custom tables, no visual editor, no DOM. Every node type, style property and node property swept against a live install and asserted on the deliv
mlola-mcp: a Model Context Protocol server that lets coding agents run browser tasks and get back what each run proves.
The generic command line and MCP server for a Latched project
Healix MCP Server — thin client, billing via Healix webapp (HEALIX_API_KEY only)
MCP server for AI agents: capture high-quality screenshots and videos of web pages, Electron apps and CLI tools, ready for README/product docs.
Playwright-based testing and evaluation framework for MCP servers
Drive your real, logged-in Chrome from any AI agent - 40 tools. Needs our Chrome extension too.
Computer use for any agent: an MCP server that drives browsers, macOS apps, Windows apps and Electron apps through their accessibility trees.
MCP server for Kapture browser automation
Give browser tasks to TabRunner, an agent in your own Chrome that uses your logins.
MCP server for generating Playwright tests
JS reverse engineering MCP server with agent-first tool design and built-in anti-detection. 为 AI Agent 设计的 JS 逆向 MCP Server，内置反检测。
Browser automation where an LLM plans and Jev (Typesafe System One) makes every per-step decision. Library, CLI and MCP server.
Salesforce documentation agent for Claude Code: a subagent that answers from the official Salesforce docs (developer, architect, Help, admin, SLDS) with verbatim, grep-checked quotes and their URLs. No API key, no MCP server.
MCP server for parallel browser automation with isolated Playwright sessions