Other · Local MCP server

Browsegrab

Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.ArkNill/browsegrab
Version
0.1.1
Status
Active
Category
other
Transport
stdio (local process)
Package
PyPI
Published
2026-03-18
Updated
2026-03-18
Publisher
ArkNill (GitHub) · 7 servers with pages here
Listed under
Browser automation MCP servers
Repository
github.com/QuartzUnit/browsegrab
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIbrowsegrab0.1.1stdioNone declared

How to connect Browsegrab

Browsegrab runs locally from a Python package published to PyPI: browsegrab version 0.1.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx browsegrab.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "browsegrab": {
      "command": "uvx",
      "args": [
        "browsegrab"
      ]
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from ArkNill (GitHub)

All 7 →
ServerRunsEndpoint or package
DiffgrabWeb page change tracking with structured diffs. markgrab + snapgrab integration.Local · stdioPyPI: diffgrab
DocpickSchema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.Local · stdioPyPI: docpick
EmbgrepLocal semantic search — embedding-powered grep for files, zero external services.Local · stdioPyPI: embgrep
FeedKitRSS/Atom feed collection with 417 curated feeds. Python MCP server.Local · stdioPyPI: feedkit
MarkGrabUniversal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.Local · stdioPyPI: markgrab
SnapgrabURL to screenshot with metadata. Python MCP server. Claude Vision optimized.Local · stdioPyPI: snapgrab

More other servers

All 6,730 →
ServerRunsEndpoint or package
Bristlecone LogicMicro-settled web content extraction and JSON schema validation utilities for AI agents via XRPL.Local · stdioPyPI: bristlecone-mcp
Brivvy MCPBrivvy MCP (OAuth): on-brand AI content, voice rules, templates, glossary.Remote · HTTPmcp.brivvy.io
Brixa StudioYour design, automated endlessly. Design anywhere, Brixa freezes it as a template, publishes forever.Remote · HTTPmcp.brixastudio.com
brokreAI-safe credential broker for MCP — run saved SSH/MySQL/psql aliases; passwords never reach AI.Local · stdionpm: brokre
BrowsenticHands your real, logged-in browser to your agent: an AI side panel extension, also over MCP.Local · stdionpm: browsentic
Browser Devtools MCPPlaywright browser & Node.js MCP. ARIA refs, screenshots, ref-based interactions.Remote & Local · HTTP, stdiox
Browser GatewayAI browser tools with Chrome CDP. Navigate, screenshot, interact. Multi-provider failover.Local · stdionpm: browser-gateway
Browser MCPControl a local headless Chrome browser: open pages, read titles, and take screenshots.Local · stdionpm: @mrfentmen/browser-mcp