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
MCP server for AI agents: high-fidelity web search (Exa) + tiered web fetch (Exa → optional local browser → Firecrawl) with an SSRF guard. A drop-in replacement for built-in WebSearch/WebFetch. Runs locally from the web-retrieval-mcp Python package. Needs 2 environment variables to run.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 140 tokens together
Stealth Chrome for agents: browse, scrape, log into and click through sites behind Cloudflare/DataDome/PerimeterX, JavaScript SPAs and login walls. Bundles the vibatchium skill and the vb mcp server. Requires the vb CLI (pipx install 'vibatchium[all]').
prkharueh12/playwright-cli-custom-agents
Agent Claude Code
Use this agent when you need to create automated browser tests using Playwright. Examples: Context: User wants to test a login flow on their web application. user: 'I need a test that logs into my app at localhost:3000 with username [email protected] and password 123456, then verifies the dashboard page loads' assistant…
serkan-ozal/browser-devtools-claude
Plugin Claude Code
Bundles 7 skills, 6 agents, 2 MCP servers · 364 tokens together
Multi-platform DevTools MCP: Playwright browser automation and non-blocking Node.js backend debugging for Claude Code.
Plugin Claude Code
Bundles 5 skills, 2 hooks · 106 tokens together
Testing system for WordPress sites — functional, performance, accessibility, shop, and AEO tests via Playwright MCP.
Agent Claude Code
Generate comprehensive retro specifications of live websites by browsing with Playwright MCP, capturing structure, content, functionality, and creating architectural documentation.
MCP server Claude CodeCodexCursor +2
MCP server for full computer control - OODA loop enabled. CLI, CRUD, Filesystem, Screen capture, Input simulation, Window management, Clipboard, and System operations. Runs locally from the mnehmos.ooda.mcp npm package.
Anshumaan031/Web-knowledge-Crawler
MCP server Claude CodeCodexCursor +2
A web crawler using Model Context Protocol (MCP). Runs locally from the crawl4ai-mcp Python package.
tolik-unicornrider/mcp_scraper
MCP server Claude CodeCodexCursor +2
Download website to a local directory (including all css, images, js, etc.). Runs locally from the website-scraper npm package.
MCP server Claude CodeCodexCursor +2
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
A Model Context Protocol (MCP) server for WaterCrawl, enabling AI systems to perform web crawling and search operations. Runs locally from the @watercrawl/mcp npm package.
MCP server Claude CodeCodexCursor +2
An MCP server that enables AI agents to automate VSCode by allowing them to interact with the UI, execute commands, inspect the DOM, and control the editor programmatically. Runs locally from the vscode-automation-mcp npm package.
MCP server Claude CodeCodexCursor +2
Model Context Protocol (MCP) integration for Scraper.is - A web scraping tool for AI assistants. Runs locally from the scraperis-mcp npm package.
mixophrygian/browser_history_mcp
MCP server Claude CodeCodexCursor +2
MCP server that gives any LLM agent full browser control via browser-use. Auto-state after every action. Runs locally from the browser-mcp-server Python package.
Plugin Claude Code
Pure-Go MCP server that turns any web page into clean, token-budgeted Markdown for AI agents — no Chromium, no V8, no Node.
Plugin Claude Code
Bundles 1 skill · 67 tokens together
Let your AI coding agent debug what already happened in your real browser. peek records masked rrweb sessions of your real browser to a local store and exposes them (DOM history, console/network errors, the action before an error, session-to-Playwright repro) to coding agents over MCP — and, with per-origin consent…
Skill Claude Code
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
Plugin Claude Code
Bundles 1 skill, 1 command, 2 hooks, 1 MCP server · 352 tokens together
Drive your real Chrome from Claude Code — movable/hideable HUD plus occlusion-aware cursor control that clicks through JS overlays, scrims and sticky bars. Bundles the ChromeBoost MCP server, permission allowlist, and usage skill.
MCP server Claude CodeCodexCursor +2
Brocogni -- Making Playwright make sense to AI agents. MCP server for semantic browser observation and self-healing selectors. Runs locally from the browser-cognition-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-tauri-automation" as configured in Radek44/mcp-tauri-automation. Runs locally from the mcp-tauri-automation npm package.
Skill Claude Code
Use this skill when the user asks to interact with a browser, take screenshots, inspect a page, capture network traffic, detect frameworks, click elements, fill forms, record browser sessions, or automate any browser task. Orchestrates Crawlio Browser's 150 browser tools via the search + execute + connecttab interface.
MCP server Claude CodeCodexCursor +2
Real signed-browser automation for AI agents, over a local stdio MCP server. Runs locally from the @uindow/cli npm package.
MCP server Claude CodeCodexCursor +2
Local OCR & screen understanding for agents: read any window, find what to click. No uploads. Runs locally from the macos-vision-mcp npm package.
tianhetonghua/Charles-mcp-server
MCP server Claude CodeCodexCursor +2
A local connector for Charles Proxy, a tool that records and inspects network traffic from applications. It provides checkpoint timelines and collects only new traffic for analysis by an AI agent.
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: