browsegrab

by QuartzUnit · MCP 服务器 · ★ 6

About browsegrab

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 MarkGrab's HTML-to-markdown conversion to achieve 5-8x fewer tokens per step compared to alternatives like browser-use.

accessibilityai-agentbrowser-automationlocal-llmmcpplaywrightpythonweb-scraping

Quick Facts

Stars6
Forks1
LanguagePython
CategoryMCP 服务器
LicenseMIT
Quality Score40.25/100
Open Issues2
Last Updated2026-04-15
Created2026-03-19
Platformsbrowser, mcp, python
Est. Tokens~6k

More MCP 服务器 Tools

Explore other popular mcp 服务器 tools:

View all MCP 服务器 tools →

Popular Python Agent Tools

Frequently Asked Questions

What is browsegrab?

browsegrab is Token-efficient browser agent for local LLMs — Playwright + accessibility tree + MarkGrab, MCP native.. It is categorized as a MCP 服务器 with 6 GitHub stars.

What programming language is browsegrab written in?

browsegrab is primarily written in Python. It covers topics such as accessibility, ai-agent, browser-automation.

How do I install or use browsegrab?

You can find installation instructions and usage details in the browsegrab GitHub repository at github.com/QuartzUnit/browsegrab. The project has 6 stars and 1 forks, indicating an active community.

What license does browsegrab use?

browsegrab is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse MCP 服务器 tools