io.github.ArkNill/browsegrab
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
750 servers in this category
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, etc.). Supports Serper, Tavily, and SearXNG.
This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.
Web page change tracking with structured diffs. markgrab + snapgrab integration.
Bridge Claude Code with Perplexity Comet for autonomous browsing and tab management
MCP server for Zen Browser automation via WebDriver BiDi
MCP tool for Google search and webpage content extraction using Chrome browser. Works with Claude to enable Google search and content fetching capabilities.
MCP server that connects to the GoLogin API
MCP server for web content fetching, summarizing, comparing, and extracting information
MCP server for using ScrAPI to scrape web pages.
Publish AI-made web pages and share files as short links from any MCP client.
MCP server for Kapture browser automation
Google search, news, maps, scholar and public webpages for AI agents, with Markdown results.
Hosted Crawleo MCP (remote streamable HTTP endpoint).
Local browser automation for MCP clients powered by DrissionPage.
Fetch any page's HTML or AI-parsed JSON, Google results, or 100+ site plugins via ScrapeUnblocker
这是一款基于 Playwright 开发的小红书自动搜索和评论工具,作为 MCP Server,可通过特定配置接入 MCP Client(如Claude for Desktop),帮助用户自动完成登录小红书、搜索关键词、获取笔记内容及发布AI生成评论等操作。
Search and fetch tools for one website, served from an index you build with the mcpmysite crawler.
Load testing and synthetic monitoring platform: test with Playwright, Browser Bot, or Protocol Bots.
Multi-session browser MCP — 15 parallel isolated browsers, 37 tools, stealth, self-improvement.