Chrome MCP MCP — ユースケース, インストール & ライブデモ

なぜ使うのか

主な機能

Uses your logged-in Chrome — no OAuth dance, no bot detection
Semantic search across all open tabs
Full DOM extraction + screenshot tools
Works on sites that block Playwright/Puppeteer
Local — no cloud middleware

ライブデモ

実際の動作

mcp-chrome.replay ▶ 準備完了

0/0

インストール

クライアントを選択

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "mcp-chrome": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-chrome-bridge"
      ]
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config を開く。保存後、アプリを再起動。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "mcp-chrome": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-chrome-bridge"
      ]
    }
  }
}

Cursor は Claude Desktop と同じ mcpServers スキーマを使用。プロジェクト設定はグローバルより優先。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "mcp-chrome": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-chrome-bridge"
      ]
    }
  }
}

Cline サイドバーの MCP Servers アイコンをクリックし、"Edit Configuration" を選択。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-chrome": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-chrome-bridge"
      ]
    }
  }
}

Claude Desktop と同じ形式。Windsurf を再起動して反映。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "mcp-chrome",
      "command": "npx",
      "args": [
        "-y",
        "mcp-chrome-bridge"
      ]
    }
  ]
}

Continue はマップではなくサーバーオブジェクトの配列を使用。

~/.config/zed/settings.json

{
  "context_servers": {
    "mcp-chrome": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mcp-chrome-bridge"
        ]
      }
    }
  }
}

context_servers に追加。保存時に Zed がホットリロード。

claude mcp add mcp-chrome -- npx -y mcp-chrome-bridge

ワンライナー。claude mcp list で確認、claude mcp remove で削除。

ユースケース

実用的な使い方： Chrome MCP

Do research on sites that require login without handing Claude your password

👤 Researchers, analysts using subscription content ⏱ ~20 min beginner

使うタイミング： You're logged into a paywalled site or gated dashboard and want Claude to read it.

前提条件

Chrome extension installed — Install from Chrome Web Store; the bridge MCP auto-connects
Target site already open and authenticated in Chrome — Log in manually in a regular tab first

フロー

Confirm tabs

List my open Chrome tabs.✓ コピーしました

→ Tab titles + URLs for every active tab
Extract

From the Bloomberg tab, extract the article body and the sidebar data table.✓ コピーしました

→ Structured content pulled; no "cannot access" error
Cross-tab synthesis

Across the 3 research-provider tabs I have open, what's the consensus view on X?✓ コピーしました

→ Synthesis with per-tab citations

結果： Answers backed by real authenticated content, no scraping of login pages.

注意点

Session expires mid-task — Extension surfaces a refresh prompt; reauth in that tab and retry

組み合わせ： memory

Catch UI regressions by screenshotting flows in your dev build

👤 Frontend engineers ⏱ ~30 min intermediate

使うタイミング： You just shipped a CSS refactor and want a visual diff on 10 core pages.

フロー

Open baseline

Open my dev site pages listed in /qa/flows.json and screenshot each into /screenshots/before/.✓ コピーしました

→ Screenshots captured with filenames matching URLs
Compare

After I deploy, take fresh screenshots and diff against /screenshots/before/. Summarize visual changes per page.✓ コピーしました

→ Per-page diff report with concrete observations

結果： A visual-regression report in 5 minutes, using your real browser environment.

注意点

Screenshots differ due to font loading — Add a sleep or wait_for_selector step before capturing

組み合わせ： filesystem

組み合わせ

他のMCPと組み合わせて10倍の力を

mcp-chrome + filesystem

Save extracted pages to disk for later indexing

Extract this tab and write to /research/ai-paper-notes.md.✓ コピーしました

mcp-chrome + memory

Remember key findings across browsing sessions

Summarize what I read today and store it in memory.✓ コピーしました

ツール

このMCPが提供する機能

ツール	入力	呼び出すタイミング	コスト
list_tabs	none	Start of any session to see what's available	free
read_tab	tab_id: int	Pull content from a specific tab	free
click	tab_id, selector: str	Interact with page elements	free
screenshot	tab_id, full_page?: bool	Visual capture for diff or review	free
search_tabs	query: str	Find which tab discusses X	free

コストと制限

運用コスト

APIクォータ: Local — unlimited
呼び出しあたりのトークン: DOM extracts can be large; 5k–50k tokens
金額: Free
ヒント: Use read_tab with selector to scope extraction instead of pulling the full DOM

セキュリティ

権限、シークレット、影響範囲

最小スコープ： chrome.tabs chrome.scripting

認証情報の保管： None — Chrome holds the sessions

データ送信先： Tab contents flow through the MCP client to your LLM provider

絶対に付与しない： access to incognito without reason

Extension has broad access by design — only install from the official Chrome Web Store listing

トラブルシューティング

よくあるエラーと対処法

Extension not detected

Pin the extension; the bridge binary needs the extension polling for it

確認： chrome://extensions shows it enabled

Tab content is blank

Page may use shadow DOM — try read_tab with include_shadow=true

Clicks don't register

Site uses anti-automation (Cloudflare, etc). Try scrolling to trigger lazy-load first.

代替案

Chrome MCP 他との比較

代替案	代わりに使う場面	トレードオフ
chrome-devtools MCP	You want the devtools protocol (console, network, perf) not user automation	DevTools MCP doesn't drive the UI — it inspects it
playwright MCP	You want headless automation in CI	No auth state; bot-detection prone

その他

リソース

📖 GitHub の公式 README を読む

🐙 オープンな issue を見る

🔍 400以上のMCPサーバーとSkillsを見る