How do I install the tool?
Install globally with `npm install -g downmarked` or run directly with `npx downmarked fetch <url>`.
@paradiselabs-ai
基本情報
Scrape any developer documentation and save it locally as a markdown file using anthropic's MCP to standardize communication between the cli and the documentation server
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"WhatsUpDoc": {
"command": "npx",
"args": [
"downmarked",
"fetch",
"https://reactjs.org/docs/getting-started.html"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
WhatsUpDoc is a command-line tool that fetches developer documentation from any website, converts it to Markdown using the Model Context Protocol (MCP), and saves it locally. It is intended for developers who want to store documentation offline or as local Markdown files.
Install globally with npm install -g downmarked, then run downmarked fetch <url> to fetch and save documentation. Use options like -o for output path, -s for a CSS selector, -r for recursive linked pages, -d for max depth, and --split to split by headers into separate files.
Install globally with `npm install -g downmarked` or run directly with `npx downmarked fetch <url>`.
Options include `-o` for output path, `-s` for a CSS selector, `-r` for recursive fetching, `-d` for maximum recursion depth (default 3), and `--split` to split by headers into separate files.
Yes, use the `-s` option with a CSS selector (e.g., `-s "main"`) to target specific content areas.
The `-r` flag fetches linked documentation pages from the initial page, up to an optional maximum depth (`-d`).

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
Remote MCP server from OSIR, an ICANN-accredited registrar: 105 tools and 11 prompts to search, register, renew, transfer, and manage domains, DNS, VPS, email, and websites from Claude, ChatGPT, Cursor, or any MCP client

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Agent Trust — open profile + reference implementation for proving what an autonomous AI agent is authorized to do: identity, delegation with attenuation, proof-of-possession, attestations, tamper-evident provenance. Buil
コメント