Attach to an already-running Chrome browser via DevTools Protocol for automation, preserving login state, cookies, and extensions. Enable remote debugging in Chrome first.
MIT
744,998 tools. Updated 2026-11-05 02:13
"MCP server for browser automation via Chrome DevTools" matching MCP tools:
- Launch a persistent browser session that remains active across automation steps, preserving cookies, tabs, and page state until explicitly closed.MIT
- Launch a persistent SeleniumBase browser session via CDP for automation workflows. Required before using interaction tools, preserving state across sessions.MIT
- Mints a single-use connect URL for Spicrawl's remote browser, letting your code drive it via Puppeteer or Playwright over Chrome DevTools Protocol.Apache 2.0
- Creates a headless Chrome browser instance and returns connection details for driving it with agent-browser or Playwright, plus a live view URL to watch and share.Apache 2.0
- List managed Chrome browser profiles for a customer, including OS, platform, and user email.Apache 2.0
Matching MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server for browser automation using Playwright to control Chrome browsers.1046 npmMIT
- AlicenseAqualityCmaintenanceEnables AI coding assistants to control and inspect a live Chrome browser for automation, debugging, performance analysis, and screenshot capture through Chrome DevTools.261,876,272 npm3Apache 2.0
Matching MCP Connectors
Programmatic headless browser sessions: create, interact, browse, and extract - rendered in a real
A real Chromium browser agents can pay for per action over x402 (USDC on Base): navigate $0.005, extract $0.005, accessibility snapshot $0.005, act $0.01, screenshot $0.02, close free. Also runs free self-hosted over stdio via npx @scriptmasterlabs/agent-browser. Six tools with structured error codes and a public receipts log. Source: https://gitlab.com/timothy.walton45/agent-browser
- Control web browsers via Chrome DevTools Protocol using DOM selectors for reliable automation. Navigate, click, type, read text, and manage tabs.MITDestructive
- Starts a browser, Electron, or mobile app automation session, replacing the active one unless told to keep it. Optionally opens a URL or attaches to running Chrome.MIT
- Retrieve visible text from the current device screen, excluding browser chrome, for content analysis and automation workflows.MIT
- Guides setup and use of agent-browser CLI for automated browser tasks like navigating pages, clicking, and capturing console errors in a real browser.MIT
- Opens the MCP-controlled Chrome browser for automation. Safe to call when the browser is already open.Apache 2.0Destructive
- Diagnose system health across Database, VideoEngine engine, Chrome browser stream, and Multi-Agent MCP client registries.MIT
- Automate website interactions in Chrome by giving an AI agent a task prompt and optional iteration limit.Apache 2.0
- Upload local files to browser file inputs using Chrome DevTools Protocol, bypassing the invisible native file picker that would hang the renderer.MIT
- Launch a persistent browser session for automation. Call this before page interactions; the session stays active across calls until closed.MIT
- Disconnect from a Chrome browser without closing it, keeping all tabs active for future reconnection.MIT
- Launch an existing Dolphin{anty} browser profile by name or ID, with optional automation for driving pages via Chrome DevTools Protocol.MIT
- Check if a Chrome instance with a remote debugging port is available for LinkedIn session recovery. Reports status or the command to launch Chrome correctly.Academic Free v1.1
- Start a persistent browser session before automating web tasks, maintaining cookies, tabs, and state across subsequent interactions via CDP.MIT
- Prepare Chrome or Edge for automated agent use by creating a dedicated profile and copying cookies, so the agent opens the browser with your sites logged in.GPL 3.0
- Sets Tencent Cloud console authentication cookie and optional csrfCode for cluster search via DMC.MIT