Chrome MCP MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

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

라이브 데모

실제 사용 모습

mcp-chrome.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/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 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

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

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

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

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

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

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

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

context_servers에 추가. 저장 시 Zed가 핫 리로드.

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

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: Chrome MCP

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

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

언제 쓸까: You're logged into a paywalled site or gated dashboard and want Claude to read it.

사전 조건

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

흐름

Confirm tabs

List my open Chrome tabs.✓ 복사됨

→ Tab titles + URLs for every active tab
Extract

From the Bloomberg tab, extract the article body and the sidebar data table.✓ 복사됨

→ 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?✓ 복사됨

→ Synthesis with per-tab citations

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

함정

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

함께 쓰기: memory

Catch UI regressions by screenshotting flows in your dev build

👤 Frontend engineers ⏱ ~30 min intermediate

언제 쓸까: You just shipped a CSS refactor and want a visual diff on 10 core pages.

흐름

Open baseline

Open my dev site pages listed in /qa/flows.json and screenshot each into /screenshots/before/.✓ 복사됨

→ Screenshots captured with filenames matching URLs
Compare

After I deploy, take fresh screenshots and diff against /screenshots/before/. Summarize visual changes per page.✓ 복사됨

→ Per-page diff report with concrete observations

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

함정

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

함께 쓰기: filesystem

조합

다른 MCP와 조합해 10배 효율

mcp-chrome + filesystem

Save extracted pages to disk for later indexing

Extract this tab and write to /research/ai-paper-notes.md.✓ 복사됨

mcp-chrome + memory

Remember key findings across browsing sessions

Summarize what I read today and store it in memory.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
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

비용 및 제한

운영 비용

API 쿼터: Local — unlimited
호출당 토큰: DOM extracts can be large; 5k–50k tokens
금액: Free
팁: Use read_tab with selector to scope extraction instead of pulling the full DOM

보안

권한, 시크릿, 파급범위

최소 스코프: chrome.tabs chrome.scripting

자격 증명 저장: None — Chrome holds the sessions

데이터 외부 송신: Tab contents flow through the MCP client to your LLM provider

절대 부여 금지: access to incognito without reason

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

문제 해결

자주 발생하는 오류와 해결

Extension not detected

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

확인: 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.

대안

Chrome MCP 다른 것과 비교

대안	언제 쓰나	단점/장점
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

Chrome MCP