Chrome-devtools-mcp의 주위에 생산 ready 래퍼. chrome-devtools-mcp는 브라우저 MCP 도구를 제공하지만 Chrome 공정 관리, 멀티 세션 공유 및 오류 복구를 완전히 나타낸다. 이 프로젝트는 운영 레이어를 추가하므로 AI 에이전트는 브라우저를 안정적으로 사용할 수 있습니다.

한국어

베어 크롬-devtools-mcp에 이 추가하는 것

Chrome Lifecycle 관리

• 시스템의 Auto-find Chrome(macOS/Linux/Windows, Edge/Brave/Arc/Chromium 포함 10+ 경로 검색)
• Lazy start - Chrome은 에이전트 시작에 첫 번째 tools/call에 출시됩니다.
• 다중 에이전트 세션은 browser.lock 참조 계산을 통해 하나의 크롬 인스턴스를 공유
• Chrome을 자동으로 닫는 마지막 세션
• 대리인 충돌 후에 안장 없음: 부모 심박수 탐지 + 시작 orphan 과정 cleanup
• WSL / 헤드리스 리눅스 : 자동 감지 및 DISPLAY 구성 (WSLg, Wayland, X11)

오류 복구

• CDP 포트 프로브를 통해 Chrome 충돌 감지 - 혼자 오류 텍스트를 신뢰하지
• 확인된 충돌 → 자동 중단 크롬, 다시 쓰기 MCP 응답 에이전트 re-navigate
• MCP stale 상태 (닫는 닫히는 탭) → MCP 아이 과정, Chrome 체재만 재시작하십시오

my-agent-browser

Production-ready wrapper around chrome-devtools-mcp. chrome-devtools-mcp provides the browser MCP tools, but leaves Chrome process management, multi-session sharing, and fault recovery entirely to you. This project adds the operational layer so AI agents can use the browser reliably.

中文文档

What this adds over bare chrome-devtools-mcp

Chrome Lifecycle Management

• Auto-find Chrome on your system (macOS/Linux/Windows, searches 10+ paths including Edge/Brave/Arc/Chromium)
• Lazy start — Chrome only launches on first tools/call, not at agent startup
• Multiple agent sessions share one Chrome instance via browser.lock reference counting
• Last session to exit automatically closes Chrome
• No orphans after agent crash: parent heartbeat detection + startup orphan process cleanup
• WSL / headless Linux: auto-detect and configure DISPLAY (WSLg, Wayland, X11)

Fault Recovery

• Chrome crash detection via CDP port probe — never trusts error text alone
• Confirmed crash → auto-relaunch Chrome, rewrite MCP response to tell agent to re-navigate
• MCP stale state (referencing closed tab) → restart only the MCP child process, Chrome stays
• Profile lock leftover (SingletonLock after hard kill) → auto-clean before launch

Config-driven + Anti-detection

• Headless mode, proxy, viewport size, custom launch args — all Chrome startup flags configurable
• evaluate_script stack traces are stripped of the pptr: marker and the MCP install path (which normally leaks your OS username) — measured against a site-origin trap, see anti-detection.md
• Flag recommendations backed by one-flag-at-a-time measurements rather than folklore
• Direct connection to existing Chrome (browserUrl mode, for pre-authenticated long-lived sessions)
• Opt-in background tabs via mcp.backgroundNewPages (default false), preserving explicit per-call choices

Agent Workflow Guidance (SKILL.md)

• Heavy pages: file-based snapshots to prevent DOM overflow crashes
• Error recovery: stale UIDs, timeouts, Chrome restart — correct response for each
• Multi-tab: open/extract/close pattern, UID isolation between tabs
• Scraping: URL-based pagination, lazy-load triggering, JS extraction
• Login flows: persistent profile, automated credentials, connect to existing session

Install

npx skills add briqt/my-agent-browser -g -y
npm install -g [email protected]
mkdir -p ~/.config/agent-skills/my-agent-browser
cp ~/.agents/skills/my-agent-browser/config.example.json ~/.config/agent-skills/my-agent-browser/config.json

Then register the MCP server in your agent:

Claude Code

claude mcp add browser -s user -- node ~/.agents/skills/my-agent-browser/scripts/start-mcp.js