7,463 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
MCP server Claude CodeCodexCursor +2
Real Chrome profiles with site intelligence — already logged in, PII anonymization, sessions persist. Runs locally from the pagerunner npm package.
MCP server Claude CodeCodexCursor +2
Web data for AI agents: scrape, crawl, search, deep research, site monitoring, browser automation. Runs locally from the @anakin-io/mcp npm package. Needs 1 environment variable to run.
Skill Claude CodeCodex
Control the user's real local browser through the Vibe Browser CLI bridge. Use for ANY task against the user's own Vibe-connected browser — their tabs, cookies, logged-in sessions, extensions, opening pages, snapshots, clicks. ALWAYS load this skill before responding to a browser request, so you can recover the user's…
MCP server Claude CodeCodexCursor +2
Undetectable browser automation for LLM agents, spoken over MCP. Runs locally from the zendriver-mcp Python package.
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
MCP server Claude CodeCodexCursor +2
Local Playwright browser through residential proxies — agent picks country + sticky identity. Runs locally from the aethyn-browser-mcp npm package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server for browser automation with AI agent. Runs locally from the runbook-ai-mcp npm package.
sendblue-api/sendblue-browser-use
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 75 tokens together
Stealth-patched Chromium daemon with REST API + CDP attach. Passes typical Cloudflare Turnstile and similar low-friction checks; not for hostile scraping at scale.
Skill Claude Code
How to run and drive this app to verify UI/server changes at runtime.
wrsmith108/dev-browser-claude-skill
Skill Claude CodeCodex
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
JMY2003/a-skill-to-do-anything-in-xiaohongshu
Skill Codex
Browser-based Xiaohongshu automation for any web-supported operation: persistent-login browser control, reusable CDP sessions, search and browsing, note detail collection, comments, likes, favorites, notification interaction, friend chat, batch operation plans, content drafting, image/card generation, and publishing.…
luispintoapify/ecommerce-agent-starter
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 261 tokens together
Give an AI agent live product data: price, stock, rating, and images from retailer pages, over the Apify MCP server. Two skills, a field map built from live runs, and copy-paste system prompts.
OpenAnalystInc/10x-Research-Skill
Plugin Claude Code
Bundles 4 skills, 12 commands · 461 tokens together
Team 10x.in research system for autonomous deep research, content creation, web scraping, and AI image generation. Supports MCP-first workflows with Tavily, Firecrawl, and Playwright plus local fallback scripts and brand-aware delivery.
Plugin Claude Code
Bundles 1 skill, 20 commands, 1 agent, 7 hooks, 3 MCP servers · 513 tokens together
A browser companion for AI assistants. Bundled MCP tools for Chrome automation, persistent project memory (Continuum chain), and an in-page hint modal — pair with the Mochi Chrome extension.
Skill Claude CodeCodex
Use Novada MCP tools for web tasks. Covers tool selection (search vs extract vs crawl vs map vs research), key parameters, common workflows, and when NOT to call each tool. Trigger: any task requiring web data, content extraction, site crawling, or multi-source research.
MCP server Claude CodeCodexCursor +2
Pixel-level browser automation MCP server for WSL2 — drive a real Chrome with screenshot + xdotool, no CDP. Runs locally from the hermes-computer-use Python package.
MCP server Claude CodeCodexCursor +2
Lets the agent fetch a URL and read its content as markdown. Runs locally from the mcp-server-fetch Python package.
Grasseed/google-search-browser-use
Skill Claude CodeCodex needs its repo
Use Chrome DevTools Protocol to allow the AI to "ask Gemini" or "research with Gemini" directly. This uses the user's logged-in Chrome session, bypassing API limits and leveraging the web interface's reasoning capabilities.
mrgoonie/screenshotone-mcp-server
MCP server Claude CodeCodexCursor +2
TypeScript Model Context Protocol (MCP) server for ScreenshotOne. Includes CLI support and extensible structure for connecting AI systems (LLMs) to ScreenshotOne API. Runs locally from the screenshotone-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
It parses the html and collects the requested data as desired. Runs locally from the muninn npm package.
ctrlShiftBryan/chrome-devtools-mcp
Plugin Claude Code
Bundled plugins for actuating and debugging the Chrome browser.
MCP server Claude CodeCodexCursor +2
Browser screenshot tool using Playwright async API. Runs locally from the brosh Python package.
MCP server Claude CodeCodexCursor +2
MCP server that connects to your browser for real-time DOM, CSS, layout inspection, screenshot capture, and Figma design comparison — your IDE's AI agent sees exactly what users see. Runs locally from the browser-lens-mcp npm package.
Dominic-Pi-Sunyer/web-speed-agent
MCP server Claude CodeCodexCursor +2
Local browser automation + Web Speed API integration for authenticated web extraction. Runs locally from the web-speed-agent Python package.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: