437 servers
Native Safari browser automation for AI agents — 80 tools, zero Chrome overhead.
Scrape, crawl, and map websites to Markdown or JSON via local CLI.
Compile once, run forever, diff the drift. Deterministic browser automation for AI agents.
MCP server paired with a browser extension that enables AI agents to control the user's browser.
Claude in Chrome, reverse-engineered and open-source. No domain blocklist. Any Chromium browser. Same 18 MCP tools, same performance.
Drive the German tax portal ELSTER via Puppeteer: submit UStVA, prepare EUER/ESt, sync inbox.
Browse the web, directly from Cursor etc.
Enable your AI agents to scrape and parse web content dynamically, including geo-restricted sites
Real signed-browser automation for AI agents, over a local stdio MCP server.
MCP server for unpacking and analyzing Playwright trace.zip archives
webmcp-bridge is a WebMCP-focused browser app that turns remote MCP servers into browser-usable tool context, so you can discover capabilities, execute them, and expose them through navigator.modelContext for next-gen browser AI workflows.
Web scraping MCP server — scrape, extract structured data, screenshot any site with anti-bot bypass.
AI-powered web scraping and data extraction capabilities through ScrapeGraph API
Code-aware browser testing agent — 13 Playwright tools for AI code editors via MCP
AI browser automation. Write async Python to navigate, click, type, and extract data.
Pay-per-call agent APIs over x402: web scraping, token compression, and semantic cache.
AI-powered native browser with 12 MCP tools. ~30 tokens per page.
Structured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy
A comprehensive Model Context Protocol (MCP) server that enables AI assistants like Claude to perform browser automation and testing tasks using Playwright. This package bridges the gap between AI and web automation, allowing natural language instructions to be converted into reliable, executable Playwright actions.