"Setting up an MCP server in Kubernetes" 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

Provides an LLM client with self-hosted web scraping capabilities including scraping, crawling, mapping, searching, structured data extraction, browser interaction, and deep research, without reliance on paid proxy or CAPTCHA services.

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.

MyChart MCP Server

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

Enables AI agents to manage live Firefox tabs and native tab groups via MCP tools over stdio, with exact-match verification and safety constraints. It does not read page content or send browser data remotely.

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.

MCP server for Yandex Eda (food delivery) that allows checking authorization, setting delivery address, searching restaurants, viewing menus, managing cart, and placing orders with safety features.

14 tools for AI agents: transcript extraction in five formats with adjustable segment size, video metadata, video and channel search, channel browsing, in-channel search, playlists, and an asynchronous batch job for up to 4,000 transcripts. Free tier: 100 credits on signup, no card.

This MCP server enables free web search and page content extraction using real browsers, with support for multiple search engines and stealth browser backends. It provides tools for searching, fetching pages, and setting up the Camoufox stealth browser.

Drives the Gemini web app in headless Chrome to generate images from text prompts, saving the full-resolution results to disk and returning their file paths. Supports continuing an existing chat so follow-up prompts can iteratively edit the same image across server restarts.

Lets an AI agent work with your own Amazon account in a separate local browser profile — reading order history and return deadlines, looking up products, and filling or editing the cart. Purchases happen only after you click "Place order" on an approval page, and no tool can place an order on its own.

Enables AI agents to automate a browser-based kinetic typography and video editing interface, including loading lyrics, choosing styles, setting BPM, clicking controls, capturing previews, and exporting MP4 or transparent PNG sequences.

MCP server for Tilda with mass editing capabilities, combining read-only official API tools and write actions via Chrome CDP for tasks like setting Metrika, replacing code and links, publishing pages, and verifying live content.

Enables AI assistants to run complete website tasks in a real browser, returning every step, the final markdown content, and persistent tabs for follow-up calls or concurrent tasks.

Enables Claude to read and search an owners' association portal's messages, news, document archive and info pages, including listing by upload date or name and reading PDFs as text. It also provides an interactive in-chat browser plus prompts for catching up on what's new, summarising documents, and preparing for the general meeting.

Reconnect to application tabs in local Chrome, inspect verification prompts, and look up saved Ashby submission receipts by job URL.

Enables AI agents to drive interactive browser sessions and reviewed backend operations (HTTP, PostgreSQL, Kafka, S3, Kubernetes) with typed inputs, execution limits, and shared evidence journals for assessing application behavior.

Enables AI agents to operate a user's signed-in Pixieset account through natural language, including delivering galleries, booking sessions, sending contracts and invoices, and following up with clients without requiring a Pixieset API key.

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.

Enables browser automation by managing Selenium Grid browser instances (Chrome, Firefox, Edge) in Docker or Kubernetes environments. Provides secure, scalable browser control for AI agents and testing workflows.

Remote browser instances for your AI agents. Reliably complete any browser-based task at scale. Fully-control agentic browsers that spin up in seconds.

Fetches web pages from HTTP/HTTPS URLs and converts them to Markdown format. Supports both SSE and Stdio protocols for web deployments, Kubernetes environments, and desktop clients.

Enables screenshotting any URL, extracting structured page data, and setting up page monitoring alerts via pay-per-call MCP tools.