# MarkUDown

MarkUDown is a Claude Code MCP server that turns web pages into Markdown or JSON, searches Google, and crawls linked content.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 16 repo stars
- Author: Scrape-Technology
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Scrape-Technology/markudown-mcp
- Updated: 2026-11-16
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/markudown

## What it does

MarkUDown gives an AI agent MCP tools for web data collection. It can read one page, discover site URLs, follow internal links, run Google searches, and pull structured fields from a page using a natural-language request. Other tools handle URL batches, full-page screenshots, and multi-source research.

The package starts through `npx` and communicates with the Scrape Technology API over MCP stdio. A `MARKUDOWN_API_KEY` is required; a missing key produces a 401 response. `MARKUDOWN_API_URL` can override the API base address.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `MARKUDOWN_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add markudown-mcp -e MARKUDOWN_API_KEY=<MARKUDOWN_API_KEY> -- npx -y markudown-mcp
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add markudown --env MARKUDOWN_API_KEY=<MARKUDOWN_API_KEY> -- npx -y markudown-mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "markudown": {
            "command": "npx",
            "args": [
                "-y",
                "markudown-mcp"
            ],
            "env": {
                "MARKUDOWN_API_KEY": "<MARKUDOWN_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "markudown": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "markudown-mcp"
            ],
            "env": {
                "MARKUDOWN_API_KEY": "<MARKUDOWN_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e MARKUDOWN_API_KEY=<MARKUDOWN_API_KEY> markudown npx -y markudown-mcp
```
Replace <…> with your own values

## When to use it
- turn a web page into clean Markdown
- crawl internal links across a site
- search Google and process result pages
- extract structured fields from a URL
- compare content from several URLs

## Example prompts
- Read the main content from `https://example.com` and summarize it.
- Crawl `https://docs.example.com` to depth 3 and find mentions of authentication.
- Search for web scraping libraries and compare the first results.

## Similar
- [Olostep MCP Server](https://affpapa.org/en/nevibecode/mcp/olostep-mcp-server.md) — MCP server · ★ 25 repo stars
- [firecrawl](https://affpapa.org/en/nevibecode/skills/firecrawl.md) — skill · 104500 installs
- [exa](https://affpapa.org/en/nevibecode/mcp/exa.md) — MCP server · ★ 5254 repo stars
- [Kagi Search](https://affpapa.org/en/nevibecode/mcp/kagi-search.md) — MCP server
- [Webcrawl Anything](https://affpapa.org/en/nevibecode/mcp/webcrawl-anything.md) — MCP server · ★ 14 repo stars
- [scrape](https://affpapa.org/en/nevibecode/skills/brightdata-scrape.md) — skill · 11100 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
