Browsegrab MCP 서버 | PlugMCP
본문으로 건너뛰기 browsegrab
한국어 문서 · llms.txt
Token-efficient browser agent for local LLMs — Playwright + accessibility tree + MarkGrab, MCP native.
browsegrab is a lightweight browser automation library designed for local LLMs (8B-35B parameters). It combines Playwright's accessibility tree with 's HTML-to-markdown conversion to achieve compared to alternatives like browser-use.
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
어떤 도구든 어떤 에이전트에. 서버를 직접 쓰지 않는 사람을 위한 MCP 디렉터리.
제품
디렉터리
개발자
회사
2026-11-08 5-8x fewer tokens per step
Features
Token-efficient : ~500-1,500 tokens/step (vs 4,000-10,000 for browser-use)
Local LLM first : Optimized for vLLM, Ollama, and OpenAI-compatible endpoints
MCP native : Built-in MCP server with 8 browser automation tools
MarkGrab integration : HTML → clean markdown for content extraction
Accessibility tree + ref system : Stable element references (e1, e2, ...) without vision models
Success pattern caching : Zero LLM calls on repeated workflows
5-stage JSON parser : Robust action parsing for local LLM outputs
Minimal dependencies : Only playwright + httpx in core
Installation pip install browsegrab
playwright install chromium
pip install browsegrab[mcp] # MCP server support
pip install browsegrab[content] # MarkGrab content extraction
pip install browsegrab[cli] # CLI with rich output
pip install browsegrab[all] # Everything
Quick Start
Python API from browsegrab import BrowseSession
async with BrowseSession() as session:
# Navigate and get accessibility tree snapshot
await session.navigate("https://example.com")
snap = await session.snapshot()
print(snap.tree_text)
# - heading "Example Domain" [level=1]
# - link "Learn more": [ref=e1]
# Click using ref ID
result = await session.click("e1")
print(result.url) # https://www.iana.org/help/example-domains
# Type into search box
await session.navigate("https://en.wikipedia.org")
snap = await session.snapshot()
await session.type("e4", "Python programming", submit=True)
# Extract compressed content (AX tree + markdown)
content = await session.extract_content()
CLI # Accessibility tree snapshot
browsegrab snapshot https://example.com
# JSON output
browsegrab snapshot https://example.com -f json
# Extract content (AX tree + markdown)
browsegrab extract https://en.wikipedia.org/wiki/Python
# Agentic browse (requires LLM endpoint)
browsegrab browse https://example.com "Find the about page"
MCP Server browsegrab-mcp # Start MCP server (stdio)
Claude Desktop / Cursor / VS Code config:
{
"mcpServers": {
"browsegrab": {
"command": "browsegrab-mcp"
}
}
}
8 MCP tools : browser_navigate, browser_click, browser_type, browser_snapshot, browser_scroll, browser_extract_content, browser_go_back, browser_wait
How It Works
Agent Browse Loop flowchart LR
A["🌐 URL + Goal"] --> B["Navigate"]
B --> C["AX Tree Snapshot\n~200–500 tokens"]
C --> D{"LLM\nDecision"}
D -->|"click / type / scroll"| E["Execute Action"]
E --> C
D -->|"goal reached"| F["Extract Content\n(MarkGrab)"]
F --> G["✅ Result"]
Token Efficiency browsegrab separates structure (accessibility tree) from content (MarkGrab markdown), sending only what the LLM needs:
flowchart TD
A["Raw HTML"] --> B["Accessibility Tree"]
A --> C["MarkGrab Markdown"]
B --> D["Structure: ~200–500 tokens\nInteractive elements with ref IDs"]
C --> E["Content: ~300–800 tokens\nClean markdown · on-demand"]
D --> F["Combined: ~500–1,300 tokens/step\n⚡ 5–8× fewer than browser-use"]
E --> F
Token efficiency (measured)
Architecture browsegrab/
├── config.py # Dataclass configs (env var loading)
├── result.py # Result types (ActionResult, BrowseResult, ...)
├── session.py # BrowseSession orchestrator
├── browser/
│ ├── manager.py # Playwright lifecycle (async context manager)
│ ├── snapshot.py # Accessibility tree + ref system
│ ├── selectors.py # 4-strategy selector resolver
│ └── actions.py # navigate, click, type, scroll, go_back, wait
├── dom/
│ ├── ref_map.py # ref ID ↔ element bidirectional mapping
│ └── compress.py # AX tree + MarkGrab → compressed context
├── llm/
│ ├── base.py # LLMProvider ABC
│ ├── provider.py # vLLM, Ollama, OpenAI-compatible
│ ├── prompt.py # System prompts (~400 tokens)
│ └── parse.py # 5-stage JSON fallback parser
├── agent/
│ ├── history.py # Sliding window history compression
│ ├── cache.py # Domain-based success pattern cache
│ └── loop_guard.py # Duplicate action detection
├── __main__.py # CLI (click)
└── mcp_server.py # FastMCP server (8 tools)
Configuration All settings via environment variables (BROWSEGRAB_* prefix):
# Browser
BROWSEGRAB_BROWSER_HEADLESS=true
BROWSEGRAB_BROWSER_TIMEOUT_MS=30000
# LLM (for agentic browse)
BROWSEGRAB_LLM_PROVIDER=vllm # vllm | ollama | openai
BROWSEGRAB_LLM_BASE_URL=http://localhost:8000/v1
BROWSEGRAB_LLM_MODEL=Qwen/Qwen3.5-32B-AWQ
# Agent
BROWSEGRAB_AGENT_MAX_STEPS=10
BROWSEGRAB_AGENT_ENABLE_CACHE=true
Part of the QuartzUnit Ecosystem
Development git clone https://github.com/QuartzUnit/browsegrab.git
cd browsegrab
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
playwright install chromium
# Unit tests (no browser needed)
pytest tests/ -m "not e2e"
# Full suite including E2E
pytest tests/ -v
License
Part of the QuartzUnit ecosystem — composable Python libraries for data collection, extraction, search, and AI agent safety.
Scrapling 🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and trick Chrome Devtools Chrome DevTools for coding agents Chrome DevTools MCP MCP server for Chrome DevTools Chrome DevTools MCP MCP server for Chrome DevTools Chrome Devtools Chrome DevTools for coding agents UI TARS Desktop The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra Playwright Playwright MCP server Playwright Playwright MCP server Obscura The headless browser for AI agents and web scraping Cua Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation. Ego Lite The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero conf SeleniumBase 📊 Python APIs for Web Automation, Testing, and Scraping. CDP Mode launches a stealth browser that bypasses bot-detection/CAPTCHAs. Adds stealth to Playwright and has an MCP server for AI agents. Browser automation MCP 서버 최고의 Browser automation MCP 서버
아직 도구 목록이 없습니다. 원격 서버는 첫 상태 확인 후에 도구 목록이 생깁니다.
Browsegrab은(는) 어떻게 설치하나요? 이 페이지에서 Cursor, Claude Desktop, Claude Code 또는 VS Code용 stdio 설정을 복사합니다. PlugMCP 프록시가 아니라 게시자의 설치 방식을 사용합니다.
Browsegrab에 API 키가 필요한가요? 이 레코드에는 필수 환경 변수가 등록되어 있지 않습니다.
Browsegrab은(는) 어떤 전송 방식을 사용하나요? Browsegrab은(는) stdio를 통해 로컬에서 실행됩니다.
Browsegrab은(는) 마지막으로 언제 확인되었나요? 마지막 확인: 2026-11-08. Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
도구
10점 중 0점