awesome-repositories.com
博客
awesome-repositories.com

通过 AI 驱动的搜索,发现最优秀的开源仓库。

探索精选搜索开源替代品自托管软件博客网站地图
项目关于排名机制媒体报道MCP 服务器
法律隐私政策服务条款
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
BrowserMCP avatar

BrowserMCP/mcp

0
View on GitHub↗
5,817 星标·449 分支·TypeScript·apache-2.0·4 次浏览browsermcp.io↗

Mcp

BrowserMCP is a browser automation bridge that connects AI tools to a live browser session through a local proxy server. It implements a standardized protocol for sending commands like click, type, and navigate to a real browser instance running on the user's machine, while keeping all browsing data on the device.

The project distinguishes itself by preserving user sessions and fingerprints across automation tasks. It attaches to the user's existing browser profile to maintain cookies, logins, and authentication state, and uses the real browser's user agent, viewport, and extension context to bypass CAPTCHAs and basic anti-automation checks. All automation runs locally on the user's machine so browsing data never leaves the device.

The tool provides page interaction capabilities including clicking elements, typing text, navigating to URLs, executing JavaScript, extracting page content, and taking screenshots. It manages browser sessions by opening tabs, maintaining persistent connections across multiple AI tool invocations, and reusing existing browser profiles to avoid re-authentication.

Features

  • Browser Automation Tools - Controls a live browser session from AI tools, performing clicks, typing, and navigation on the user's behalf.
  • Browser Automation Agents - Provides a local browser agent that executes automation on the user's own machine.
  • Browser Automation - Directs a user's existing browser from an AI application without sending data to remote servers.
  • Browser Automation Tool Connectors - Attaches to an existing browser profile to maintain cookies, logins, and authentication across automation tasks.
  • Browser Automation - Executes all browser automation locally on the user's machine, keeping activity and credentials on-device.
  • Browser Proxy Bridges - Runs a local proxy server that bridges AI tool requests to the user's browser, keeping all data on-device.
  • Local Data Privacy Tools - Runs all browser automation locally on the user's machine so browsing data never leaves the device.
  • Browser Session Token Reuse - Reuses existing browser session tokens and cookies to preserve authentication across automation tasks.
  • Browser Automation Protocols - Implements a standardized protocol for sending browser automation commands to a live browser instance.
  • Browser Session Persistence - Runs all browser automation locally on the user's machine, keeping browsing data on-device.
  • AI-Driven Browser Controllers - Enables AI applications to programmatically navigate pages, fill forms, and extract data through a live browser session.
  • Browser Session Managers - Directs a live browser from an AI tool to click, type, and navigate on the user's behalf.
  • Scraping and Anti-Detection - Uses a real browser fingerprint and profile to bypass CAPTCHAs and basic anti-automation checks.
  • Browser Tab Content Extractors - Retrieves the full HTML or visible text content from the currently active browser tab.
  • Browser Page Extractors - Extracts text and structured data from live browser pages for downstream processing by AI agents.
  • Live Page Content Readers - Extracts text, attributes, and structured data from the current browser page for downstream processing.
  • Local Browser Proxies - Runs a local server that proxies AI tool requests to the user's browser, keeping all data on-device.
  • Anti-Detect Profile Managers - Uses the real browser fingerprint and profile to bypass CAPTCHAs and basic anti-bot measures during automation.
  • Anti-Bot Evasion - Uses the real browser's fingerprint and profile to bypass CAPTCHAs and basic anti-automation checks.
  • Browser Fingerprint Generators - Uses the real browser's fingerprint to avoid detection by anti-bot systems during automation.
  • Screenshot Capture - Captures screenshots of the current browser viewport and returns them as base64-encoded images.
  • JavaScript Execution Bridges - Executes arbitrary JavaScript code within a browser tab context and returns the result.
  • Tab Openers - Opens new browser tabs and returns unique identifiers for subsequent automation commands.
  • Browser Control Protocols - Implements a standardised protocol for sending commands like click, type, and navigate to a real browser instance.
  • Browser Navigation - Directs the browser to load a specified web page and waits for the page to finish loading.
  • Programmatic Page Interactions - Performs clicks, form fills, and navigation on a page through a remote agent.
  • Browser Automation - Automated control for local Chrome instances.
  • More to explore - Automate local browser

Star 历史

browsermcp/mcp 的 Star 历史图表browsermcp/mcp 的 Star 历史图表

AI 搜索

探索更多 awesome 仓库

用简单的语言描述您的需求 —— AI 将根据相关性为您从数千个精选开源项目中进行排序。

Start searching with AI

Mcp 的开源替代方案

相似的开源项目,按与 Mcp 的功能重合度排序。
  • steel-dev/steel-browsersteel-dev 的头像

    steel-dev/steel-browser

    6,450在 GitHub 上查看↗

    Steel is a cloud browser automation platform that provides a REST API for launching and controlling remote Chrome browser sessions. It enables programmatic browsing and web scraping using standard automation tools like Puppeteer, Playwright, and Selenium, connecting to cloud-hosted browser instances via WebSocket and the Chrome DevTools Protocol. The platform supports both headless and headful browser sessions, with language-specific SDKs for TypeScript and Python. The service distinguishes itself through comprehensive anti-detection capabilities, including residential proxy rotation, CAPTCHA

    TypeScriptaiai-agentsai-tools
    在 GitHub 上查看↗6,450
  • executeautomation/mcp-playwrightexecuteautomation 的头像

    executeautomation/mcp-playwright

    5,237在 GitHub 上查看↗

    This project is a Model Context Protocol server that enables Large Language Models to control Playwright browsers for web automation, scraping, and end-to-end testing. It functions as a programmable interface for executing JavaScript, capturing screenshots, and interacting with web elements across multiple browser engines. The server exposes browser automation capabilities as a set of standardized tools that models can discover and invoke. It supports session-based browser isolation to ensure unique contexts for each client connection and provides a transport layer using either standard input

    TypeScript
    在 GitHub 上查看↗5,237
  • cloakhq/cloakbrowserCloakHQ 的头像

    CloakHQ/CloakBrowser

    26,322在 GitHub 上查看↗

    CloakBrowser is a modified Chromium browser and anti-detect profile manager designed to bypass bot detection and automation signals. It serves as a replacement for standard browser engines in automation frameworks, using source-level binary patching to remove automation flags and spoof internal hardware signals. The project focuses on identity masking through the generation and maintenance of unique hardware and software fingerprints, including canvas noise and screen dimensions. It synchronizes browser timezones and locales with network proxy exit points and replaces programmatic input with

    Pythonai-agentsanti-detectantidetect-browser
    在 GitHub 上查看↗26,322
  • autoscrape-labs/pydollautoscrape-labs 的头像

    autoscrape-labs/pydoll

    6,919在 GitHub 上查看↗

    pydoll is a Chrome DevTools Protocol automation library and headless browser controller used for web data extraction and parallel browser automation. It controls Chromium-based browsers via direct WebSocket connections, allowing it to manage isolated browser contexts and tabs while bypassing the overhead and detection associated with WebDriver. The project features an anti-bot evasion framework that mimics natural human behavior, including mouse movements generated via Bezier curves and variable typing patterns. It provides specialized stealth capabilities to bypass behavioral analysis and au

    Pythonanti-detectionautomationbrowser-automation
    在 GitHub 上查看↗6,919
查看 Mcp 的所有 30 个替代方案→

常见问题解答

browsermcp/mcp 是做什么的?

BrowserMCP is a browser automation bridge that connects AI tools to a live browser session through a local proxy server. It implements a standardized protocol for sending commands like click, type, and navigate to a real browser instance running on the user's machine, while keeping all browsing data on the device.

browsermcp/mcp 的主要功能有哪些?

browsermcp/mcp 的主要功能包括:Browser Automation Tools, Browser Automation Agents, Browser Automation, Browser Automation Tool Connectors, Browser Proxy Bridges, Local Data Privacy Tools, Browser Session Token Reuse, Browser Automation Protocols。

browsermcp/mcp 有哪些开源替代品?

browsermcp/mcp 的开源替代品包括: steel-dev/steel-browser — Steel is a cloud browser automation platform that provides a REST API for launching and controlling remote Chrome… executeautomation/mcp-playwright — This project is a Model Context Protocol server that enables Large Language Models to control Playwright browsers for… cloakhq/cloakbrowser — CloakBrowser is a modified Chromium browser and anti-detect profile manager designed to bypass bot detection and… autoscrape-labs/pydoll — pydoll is a Chrome DevTools Protocol automation library and headless browser controller used for web data extraction… ultrafunkamsterdam/nodriver — nodriver is an asynchronous Chromium browser automation framework that provides headless control and web scraping… browser-use/web-ui — This project is a graphical user interface for controlling, configuring, and monitoring AI agents that automate web…