MCP Browser Automation

Name: MCP Browser Automation
Author: algonius

@algonius

MCP Browser Automation について

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

#browser-automation #mcp #open-source

基本情報

カテゴリ

ブラウザ自動化

ライセンス

Apache-2.0

ランタイム

node

トランスポート

stdio

公開者

algonius

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "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"
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

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

FAQ from MCP Browser Automation

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.