Meet your QA partnerMCP servers
Playwright MCP
Let an assistant interact with a browser for repeatable checks and exploration. Use a test account and a clearly bounded task.
Docs reviewed
YOUR MISSION
Review accessibility
An actionable accessibility issue list
Editorial starting points
Check current publisher documentation, plans and permissions before connecting. A suggested stack is not a tested integration.
The design essentialMCP servers
Figma MCP
Bring design context into your AI-assisted development workflow. Start with one frame, then review the result against the original.
Docs reviewed
Explore the community collection
18 source-reported listings in Browser Automation. Independently unverified.
Browser AutomationMCP servers
bilibili-mcp-js
A MCP server that supports searching for Bilibili content. Provides LangChain integration examples and test scripts.
Community listing
Browser AutomationMCP servers
safari-mcp
Native Safari browser automation for AI agents with 80+ tools. No Chrome dependency, optimized for Apple Silicon with 60% less CPU overhead.
Community listing
Browser AutomationMCP servers
mcp-server-browser
Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Community listing
Browser AutomationMCP servers
agent-scraper-mcp
Web scraping MCP server for AI agents. 6 tools: clean content extraction, structured scraping with CSS selectors, full-page screenshots via Playwright, link extraction, metadata extraction (OG/Twitter cards), and Google search. Free tier with x402 micropayments.
Community listing
Browser AutomationMCP servers
DOMShell
Browse the web using filesystem commands (ls, cd, grep, click). 38 MCP tools map Chrome's Accessibility Tree to a virtual filesystem via a Chrome Extension.
Community listing
Browser AutomationMCP servers
mcp-server-playwright
An MCP server for browser automation using Playwright
Community listing
Browser AutomationMCP servers
agentfetch-mcp
Token-budgeted web fetch for AI agents. Auto-routes between Trafilatura, Jina Reader, FireCrawl, and pypdf based on URL pattern. estimate_tokens before fetch_url, 6h Redis cache, server-side max_tokens truncation. Open source MCP server (MIT) plus hosted REST API at agentfetch.dev — 500 free fetches/mo, no card.
Community listing
Browser AutomationMCP servers
intercept-mcp
Multi-tier fallback chain for fetching web content as clean markdown. Handles tweets, YouTube, arXiv, PDFs, and regular pages with 9 fallback strategies.
Community listing