"Running queries in Apache Superset" matching MCP servers:

Enables AI agents and MCP clients to drive real Chrome, Edge, Brave, and Firefox browsers through native automation protocols. It exposes tools for navigation, page snapshots, form filling, clicks, screenshots, console/network inspection, and tab management.

Enables MCP clients to open websites, capture screenshots at multiple breakpoints, and run automated design audits for issues like overflow, small tap targets, low contrast, missing alt text, tiny text, and clipped content.

Enables Claude Code to control Firefox through tools for tabs, navigation, clicks, typing, scrolling, screenshots, page reading, forms, JavaScript, and console/network logs.

Enables any MCP client to drive the user's real Chrome profile through a Chrome extension bridge, with tools for navigation, accessibility snapshots, ref-based interactions, console/network reading, screenshots, tab management, and restricted script evaluation.

DREAM LAUNCHERS INTERIORS PRIVATE LIMITED

Enables local opencode agents to control a live Chrome browser via MCP tools, including tab management, JavaScript execution, clicking, form filling, page reading, screenshots, and console log retrieval.

Enables searching products, viewing orders, and analyzing order trends on Amazon.in via a persistent Playwright browser session.

Enables Claude Code to drive your everyday logged-in browser session — opening and closing tabs, navigating, clicking, typing, scrolling, filling forms, uploading files, taking screenshots, and reading page text, console output and network requests. It runs through a local native-messaging bridge, scoping each client session to its own window behind yours.

Enables Claude Code, Codex, Devin, or any MCP client to control Chrome/Edge through the repository's browser extensions, with Claude-style visual tools or Codex-style text-first tools.

MCP server that lets Claude control multiple persistent browser tabs inside VS Code, with tools for navigation, clicking, typing, snapshotting pages, and reading console output.

MyChart MCP Server

A stateless MCP server for UI/UX design inspiration, live component discovery, and modern web micro-effects, resolving queries in real time via the Serper API.

An MCP server that reads decrypted cookies from a running Chrome instance via the Chrome DevTools Protocol, returning them in various formats.

Enables any MCP-capable harness to run queries through a real browser driving real search engines in a configurable fallback chain (Google, DuckDuckGo, Bing, Baidu, Sogou), with CAPTCHA or sign-in handoff, persistent per-engine cookies, and reported provenance for each result.

Enables AI assistants to inspect values, view errors, and capture canvas output from Observable Notebook Kit notebooks running in a web browser.

Provides a web search tool with citations by running Claude Code CLI in an isolated Docker container, enabling search even in environments without direct Anthropic web search support.

Enables Claude and other MCP clients to control Safari on macOS, opening tabs, reading pages, clicking, filling forms, pressing keys, running JavaScript, and taking screenshots in the user's real signed-in browser.

Lets Claude Code attach to a running, signed-in Firefox over WebDriver BiDi to control tabs, navigate, screenshot, read pages, click, type, fill forms, evaluate JavaScript, and inspect console/network activity.

Lets an agent open a running web app in a real browser, perform literal interaction steps, capture screenshots, measure UI rules, diff frames, and store evidence, while leaving all judgment to the calling agent.

Enables web search capabilities through the Tavily API, allowing users to search the internet for information using natural language queries. Built as a demonstration MCP server running in stdio transport mode.

Gives ChatGPT, Claude and other AI assistants a real Chrome browser running in the cloud, so they can navigate, read page content, click, type, run scripts and take screenshots, with saved sessions, live viewing or takeover via remote desktop, and CAPTCHA detection.

An accessibility audit server that enforces WCAG 2.2 AA standards by running axe-core in a headless browser, providing violation details grouped by impact with fix hints.

An SSH-to-MCP bridge that lets MCP-capable agents reach Chrome tabs, optional desktop adapters, and scoped SideScreen tools running in a signed-in Windows session, routed through an authenticated loopback broker. It keeps browser and desktop processes in the interactive session while exposing their tools over an existing SSH connection.

Local stdio MCP server for Browser Control SDK, a Windows WebView2 browser with persistent profiles, explicit tab IDs, structured observations, screenshots and manual sign-in. Requires Windows, WebView2 Runtime and a running Browser Control instance (or explicit --launch); server source is in MCP/server.py.

Enables multiple Codex CLI conversations to operate on one already-running, logged-in Chrome profile, where each thread owns a colored tab group and can act only on its registered pages through scoped page tools.

Enables control of a real Chrome/Brave/Edge browser over MCP stdio through CDP — opening tabs, navigating, clicking, typing, running JS, uploading files, screenshotting, and recording actions — plus a guided Gmail flow for signing in, composing, attaching a PDF, sending, and verifying the message in Sent Mail.

An MCP server that lets an LLM build, inspect and drive a running BrowserCard deck live in the browser.

An MCP server that lets an AI agent drive and inspect a running Next.js app, with headless route/error introspection and a real DOM-based in-page bridge for interactive testing.

Enables running multiple isolated browser instances in parallel, each with independent state and auth cloning, for concurrent task execution.

Enables AI agents to drive a live, persistent self-hosted Chromium session over MCP, running browser actions via Playwright/CDP, capturing page snapshots, screenshots and videos, and managing uploads and downloads in the same tabs and signed-in accounts a human user can take over at any time.