# pinkpixel-dev-web-scout-mcp

An MCP server that searches the web through DuckDuckGo and pulls clean text out of pages. Useful when your agent needs fresh content instead of model memory.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 138
- Author: pinkpixel-dev
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/pinkpixel-dev/web-scout-mcp
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/pinkpixel-dev-web-scout-mcp

## What it does

The server exposes two tools. `DuckDuckGoWebSearch` takes a query and a result count, 10 by default, and returns titles, URLs and snippets. `UrlContentExtractor` accepts one URL or an array and returns readable text with scripts, styles and navigation stripped out.

Multiple links are fetched in parallel, and requests to the search engine are throttled so you do not get blocked. Memory is managed too, so long pages do not take the process down. You need Node.js 18.0.0 or newer plus npm or yarn.

Embedding the package and calling `createServer()` yourself? Set `WEB_SCOUT_DISABLE_AUTOSTART=1`. Otherwise the published entrypoint bootstraps the stdio transport on its own and you end up with two servers on one channel.

## Requirements
- Needs: Node.js (commands run via npx)
- Remote server: `https://server.smithery.ai/@pinkpixel-dev/web-scout-mcp/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http pinkpixel-dev-web-scout-mcp https://server.smithery.ai/@pinkpixel-dev/web-scout-mcp/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add pinkpixel-dev-web-scout-mcp --url https://server.smithery.ai/@pinkpixel-dev/web-scout-mcp/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "pinkpixel-dev-web-scout-mcp": {
            "url": "https://server.smithery.ai/@pinkpixel-dev/web-scout-mcp/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "pinkpixel-dev-web-scout-mcp": {
            "type": "http",
            "url": "https://server.smithery.ai/@pinkpixel-dev/web-scout-mcp/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http pinkpixel-dev-web-scout-mcp https://server.smithery.ai/@pinkpixel-dev/web-scout-mcp/mcp
```

## When to use it
- find fresh sources for a query and hand the agent a link list
- pull article text without ads and menus
- read a batch of pages in a single call
- feed the model current docs instead of stale memory
- collect a set of sources on a topic for later review

## Example prompts
- Search the web with web-scout for five recent MCP articles and list the links
- Extract clean text from these three pages and summarise the key points
- Look up what shipped in Node.js 22 and show me the snippets

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13169
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 12927

---
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