Control web browsers via Chrome DevTools Protocol using DOM selectors for reliable automation. Navigate, click, type, read text, and manage tabs.
MIT
Destructive
726,102 tools. Updated 2026-10-30 20:27
"browser" matching MCP tools:
- Render a URL in headless Chromium to capture a visual screenshot, console logs, errors, and page metadata for UI testing and verification.Business Source 1.1
- Automate web browser tasks: navigate to URLs, click elements, type text, take screenshots, and run JavaScript in real time.-
- List decoded text from every station fldigi's decoder bank has locked onto in the passband, including signals too weak for the waterfall. Supports PSK, RTTY, and CW.GPL 3.0
- Run headless Chromium in an offline sandbox to execute automation scripts, capture screenshots, and download generated artifacts locally.-
- Automate website interactions in Chrome by giving an AI agent a task prompt and optional iteration limit.Apache 2.0
Matching MCP Servers
- FlicenseNot gradedqualityBmaintenanceLets AI agents drive your real, already-logged-in browsers on macOS in the background without stealing focus, organizing work into tab groups, reading pages as compact accessibility snapshots, and saving repeatable scenarios. Supports Chrome, Edge, Brave, Yandex Browser, and Safari, with per-agent isolation and automatic tab cleanup.-
- AlicenseNot gradedqualityBmaintenanceEnables any agent to drive a dedicated Chromium instance through MCP, including opening and reading pages, taking steps, logging in via a password vault, downloading/uploading files, and replaying saved routines. It also gates sensitive actions behind approvals and can use client certificates or one-time card data for official procedures.MIT
Matching MCP Connectors
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
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
- Automates tasks on websites by operating a Chrome tab: reads page structure, clicks elements, fills fields, and scrolls. Use for web-based actions.MIT
- Search internet radio stations worldwide by name and country. Returns station details including URL, codec, bitrate, and tags from daily-updated public domain data.-
- Search internet radio stations by country using Radio Browser API. Returns stations with quality scores and source verification for data reliability.-
- Check the live isolated browser state, current same-origin page, authenticated identity, and proof schedule without exposing cookies.MIT
- Closes the isolated Okta browser session and deletes its temporary profile to clean up resources and maintain security.MIT
- Navigate the isolated browser to a same-origin URL or path within the Okta workspace. Rejects cross-origin navigation.MIT
- Read Okta API v1 data from the same origin using your browser session; sensitive fields like tokens and secrets are redacted.MIT
- Rent a real Chrome browser session for automation. Control it via navigate, click, type, screenshot, and stop commands. Per-minute billing.MIT
- Stop the rented browser session to end billing and prevent additional charges.MIT
- Type text into the currently focused element of a rented browser, enabling automated input.MIT
- Capture the current page of a rented browser as an image. Optionally include the full page content.MIT
- Execute JavaScript code directly in the browser and retrieve results. Supports expressions, functions, async/await, and targeting specific DOM elements for precise evaluation.MIT
- Capture browser console output by navigating to a URL, with options for real-time streaming, wait conditions, and custom browser commands.MIT
- Execute JavaScript in the live browser context to extract data, run function logic, and inspect specific DOM elements via CSS selectors.MIT
- Create a new isolated browser context with auto-generated ID, configurable type, viewport, headless mode, and target URL for automated testing or AI-assisted development.MIT