"Git for Windows" matching MCP servers:

A Windows-only MCP server for controlling a real browser using native screenshots, Windows accessibility, and node-interception mouse/keyboard input, without CDP or Playwright.

Provides a local MCP server for AI-powered web crawling on Windows, enabling agents to directly crawl and extract web content without requiring WSL.

TypeScript implementation of an MCP server that provides tools for web crawling, content extraction, and browser automation, enabling AI systems to access and process web content through 15 specialized tools.

Lets OpenCode check whether Arc is open on Windows and navigate it to absolute HTTP(S) URLs from WSL2, even when another browser is the Windows default.

Enables crawling sites from start URLs and retrieving internal and external links, file download links, HTML tables as rows, and lists, with controls for crawl depth, page limits, sitemaps, robots.txt, and proxy mode.

Enables reading and sending messages in Google Messages for web through a paired Chrome tab using chromefile, with tools for status, listing conversations, reading message history, and sending texts.

A fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. Built for AI Agents (Cursor, Claude Code, OpenCode), it uses a stealth browser engine to fetch pages, dynamically handles SPAs/React, and converts bloat into token-optimized Markdown.

Enables MCP clients to open and close applications, files, and folders on a Windows machine, manage running apps and File Explorer windows, control Chrome tabs, and perform system actions like shutdown and restart.

Gives Claude control of a real, headed Chromium browser via Playwright, enabling web navigation, clicking, typing, screenshots, and JavaScript evaluation.

Verified control of the whole desktop for agents on Windows and Linux: apps with no API, windows, shell, browser. MCP server + CLI + REST API.

Enables agents to search and read posts, images, and limited comments across Xiaohongshu, Weibo, Zhihu, and WeChat Official Accounts, with local OCR and traceable sources.

A Model Context Protocol server that provides web search capabilities using Google Custom Search API and webpage content extraction functionality.

A CDP-native MCP server that lets AI agents drive a real Chrome browser with deep network/console inspection, robust page interaction, and the ability to reverse-engineer a site's API flow into runnable code with dependency chaining and replay verification.

Enables AI agents to drive real Google Chrome with stealth and captcha handling, using Patchright to avoid bot detection.

Enables AI agents to inspect and modify Chrome state directly through extension APIs, listing tabs and windows and moving or reordering tabs within and across windows. Operations are validated and never simulate mouse/keyboard input, steal focus, or activate tabs implicitly.

Enables autonomous web form inspection and schema auto-mapping by matching input attributes, autocomplete hints, and regex validations to agent state, while also pruning DOMs and converting tables into structured JSON for web agents.

Enables controlling Windows desktop applications through the UI Automation tree with visible on-screen cursor, click, and status overlays, plus automating browsers via ego lite or Playwright/Edge. Provides 23 tools over a single MCP server for listing windows, reading controls, clicking, typing, scrolling, dragging, and browser navigation.

Desktop automation MCP server for any AI agent: control the screen, windows, mouse/keyboard, and Chrome (CDP) on your machine. Installable via npm @nuphus/nuphus-mcp.

A native Windows terminal multiplexer with MCP bridge for AI agents, enabling browser automation, multi-agent coordination, and terminal control.

Enables Claude Code to drive a real Firefox browser through a local MCP server using synthetic DOM events for clicks and typing. Supports tab management, navigation, page reading, form interaction, screenshots, and per-site consent with no network port opened.

Enables automation of Xiaohongshu (Little Red Book) operations including content publishing, searching, and interacting, with MCP protocol support for AI agent integration.

Local stdio MCP server for Browser Control SDK, a Windows WebView2 browser with persistent profiles, explicit tab IDs, structured observations, screenshots and manual sign-in. Requires Windows, WebView2 Runtime and a running Browser Control instance (or explicit --launch); server source is in MCP/server.py.

Enables ZCode to control a real Chrome browser, including tabs, navigation, page content, clicks, form filling, keyboard input, scrolling, screenshots, and JavaScript evaluation through a local MCP bridge.

Gives MCP-compatible AI agents a local, observable control plane for Edge, Chrome/Chromium, and Firefox, combining DOM/accessibility, screenshots, Windows UI Automation, and real mouse/keyboard input with verification, approvals, and audit logging.

Lets AI coding assistants control and inspect a live Chrome browser through MCP, enabling reliable automation, debugging, and performance analysis using Chrome DevTools.

Enables web AI clients and local IDEs to securely operate a local machine through an OAuth-gated MCP endpoint, with governed tools for files, shell, search, Git, SQLite, browser automation, DevTools, background tasks, localhost services, clipboard, notifications, ports, Postman, and AIObox windows.

Enables running supported Windows applications on hidden desktops and viewing their captured windows through a local Chrome dashboard, with optional PyCharm and browser automation control.

Enables Codex to operate your already-open Firefox tabs via local MCP tools for status, tab management, navigation, interaction, and screenshots on Windows x64 with Firefox 140+.

Enables ChatGPT to securely control a local workstation via an MCP tunnel, exposing 44 tools for file/project editing, git, process supervision, browser automation, and Office document handling across macOS, Linux, and Windows.

Enables an MCP client such as Claude Code to read and operate your real, everyday Firefox profile — reading pages, clicking, typing, navigating, switching tabs and taking screenshots — with per-action human approval and masking of password, one-time-code and credit card fields.

Enables secure access to Tor/onion services with content filtering and safety guardrails for AI assistants.

Enables browser automation (navigate, screenshot, click, type, etc.) for Claude Code via MCP protocol, with a Chrome extension for configuration.

Enables MCP clients to observe Windows accessibility trees and deltas, generate fail-closed semantic action plans for external authorized executors, and control isolated, agent-owned Chrome tabs without accessing personal tabs.

Enables Claude to interact with VS Code's language servers, debugger, terminals, tasks, tests, git, and a CDP-controlled Chrome browser for editor and browser automation.

Drop-in WSL-safe wrapper for @playwright/mcp that prevents Chromium GPU crashes on Windows Subsystem for Linux.

A local MCP server for Windows that gives Claude control of your screen, enabling screen viewing, image-based element finding, clicking/typing, macro recording and replaying, and scheduled automation with failsafe safety features.

Enables OpenCode to safely automate and verify Windows desktop and web browser interactions through 83 MCP tools, including UI automation, screenshots, visual diffing, workflow recording, and secret handling, with strict allowlist-based security.

Enables Hermes to privately invoke Windows MCP tools on a local PC through a Tailscale-only HTTPS path, with security checks and typed power control.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

MCP server for job search that crawls job listings using Playwright, with a fix for stdout pollution on Windows/WorkBuddy.