MCP Browser Automation

@algonius

代码仓库

基本信息

分类

浏览器自动化

许可证

Apache-2.0

传输方式

stdio

作者

algonius

关于 MCP Browser Automation

MCP browser automation server. Exposes browser control tools to external AI systems via Model Context Protocol. Open-source & secure.

#browser-automation #mcp #open-source

MCP Browser Automation 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "algonius-browser": {
      "command": "start",
      "autoApprove": [
        "click_element",
        "get_dom_extra_elements",
        "manage_tabs",
        "scroll_page",
        "type_value",
        "navigate_to"
      ],
      "disabled": false,
      "timeout": 3600,
      "url": "http://127.0.0.1:9333/sse",
      "type": "sse"
    }
  }
}

MCP Browser Automation 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,直接连接服务器端点实时获取工具列表。

概览

What is MCP Browser Automation?

MCP Browser Automation is an open-source MCP (Model Context Protocol) server that provides browser automation capabilities to external AI systems. It exposes a set of browser control tools through the MCP protocol, enabling AI assistants to navigate websites, interact with DOM elements, and extract web content programmatically.

How to use MCP Browser Automation?

Install the Chrome extension from the Chrome Web Store or build from source, then install the Go-based MCP Host using the one‑click installation script or manually. Verify the installation with mcp-host-go --version. Once installed, AI systems can invoke tools and read resources via standard MCP protocol calls.

Key features of MCP Browser Automation

MCP Protocol Integration for AI systems
Chrome Extension with background service worker
Go-based MCP Host bridging extension with external tools
5 browser automation tools plus 2 MCP resources
Full TypeScript implementation with structured error handling
Comprehensive integration tests for all functionality

Use cases of MCP Browser Automation

Web scraping: navigate to a site, get DOM state, extract elements, and interact with content
Form automation: fill input fields, click submit, and verify completion
Multi‑tab management: create, switch, and monitor multiple tabs simultaneously
Page navigation with scrolling: scroll to load dynamic content and extract newly loaded elements

常见问题

What are the system requirements?

Requires Chrome/Chromium 88+ or Microsoft Edge 88+, Node.js 22.12.0+, pnpm 9.15.1+, and Go 1.21+ (for building the MCP host).

How does MCP Browser Automation communicate with AI systems?

The Go‑based MCP Host implements the MCP protocol and communicates with the Chrome extension via Native Messaging. AI systems interact through standard MCP tool and resource calls.

What browser automation tools are available?

Five tools: `navigate_to`, `manage_tabs`, `get_dom_extra_elements`, `click_element

浏览器自动化分类下的更多 MCP 服务器

Browserbase MCP Server

browserbase

Allow LLMs to control a browser with Browserbase and Stagehand

3.4K

BitBrowser MCP service

BitBrowser01

BitBrowser MCP simple to use, no complicated procedures required. Supports a variety of intelligent agent services.

Fastcrw

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary.

286

TinyFish

tinyfish

Give your AI agent the live web. One MCP server for Search, Fetch, Browser, and Agent: browse real sites, extract structured data, fill forms, and run multi-step workflows. Search and Fetch are free.

playwright-server MCP server

blackwhite084

189