Browser Automation MCP Servers for DeepSeek Harness

Let any AI agent operate desktop apps on macOS, Windows and Linux, in the background and safely.

Fast screenshot capture tool for web pages - optimized for Claude Vision API

MCP server to manage your Tampermonkey scripts

MCP-native, model-agnostic, agentic-first, multi-engine browser-control server.

Bridge a live Chrome browser to your agent: 150 tools for capture, extraction, and observation.

Drive Chrome with filesystem commands (ls, cd, grep, click, type). One MCP tool, multi-agent.

Web content extraction and automation via Playwright MCP

Firefox MCP with auto-screenshot on every mutation tool call

MCP server for web page and cross-platform system screenshots (macOS, Linux, Windows)

MCP server for browser automation with AI agent

Playwright Tools for MCP

Visual-diff & change-detection tools that catch agentic UI drift for coding agents.

Autonomous UI debugging MCP server. Give a goal; a fast agent drives the browser/desktop, finds bugs + visual issues, and reports back.

Web navigation and verification for AI agents: page digest, typed diff per action, assertions.

Real-browser automation based on Patchright with ad blocking.

Use your existing Firefox and logged-in tabs, limited to tabs or groups you explicitly share.

Isolated multi-session Chromium runtime for external MCP clients over stdio.

MCP server for ZennoBrowser antidetect browser: manage browser profiles from AI agents

Drive an open 3DStreet scene tab from Claude Desktop or Claude Code via MCP tool calls.

Browserbase MCP server: cloud browser sessions, agents, contexts, fetch, search, functions

A real Android phone in the cloud for MCP agents: observe the screen, act, reset to a saved state.