Browser Automation MCP Servers for DeepSeek Harness

Launch, inspect, control, and share isolated cloud browsers for your agents.

An MCP server that lets AI agents act like a human at a real terminal, local or over SSH.

Secure Linux desktop automation - input, screen/OCR/vision, AT-SPI2 UI tree, window, clipboard

Capture batches of public web pages in a real browser and download the screenshots as a zip.

Agent website testing: browser QA, visual regression, Markdown extraction, and security checks.

Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover.

Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.

Native macOS browser exposing an MCP server so AI agents can drive a real WKWebView.

BrowserOxide — stealth headless browser engine in Rust (Python bindings) — real HTML/CSS/DOM/JS, own BoringSSL TLS, native fingerprint, no

Capturewren: screenshot any URL (banners removed) plus status, title and clean page text for agents.

See any site as it looks on a real iPhone, iPad or MacBook — and drive that window over MCP.

Browser automation MCP server with 84 tools. Pure CDP, DOM diffing, vision hybrid.

Clean PNG/JPEG screenshots via REST or MCP, with goal-driven multi-step navigation.

AI-controlled browser farm: N isolated Chromium instances with 36 MCP tools

Control visible, persistent Hronaut browser workspaces through a local MCP connection.

Verification browser for coding agents: headless WebKit, DOM eval, screenshots, pixel-diff.

Browser automation MCP server with 84 tools. Pure CDP, DOM diffing, vision hybrid.

A Model Context Protocol (MCP) server for Xiaohongshu (Little Red Book) automation

Full-page website screenshots and visual diffs between two captures. Pay per capture on Apify.

Screenshot API for AI agents. Any public page as image or PDF, banners hidden, 227 countries.

Your agent hit a limit? Keep working. MateMCP securely connects AI chats to your computer via MCP.