MCP Web Tools
# MCP Web Tools
A powerful MCP (Model Context Protocol) server that gives AI agents web superpowers. Extract content, search the web, monitor sites, and convert HTML to markdown — all through a clean tool interface.
## Tools
| Tool | Description |
|------|-------------|
| `web_extract` | Extract structured content from any URL (title, headings, paragraphs, links, images, metadata) |
| `web_search` | Search the web via DuckDuckGo — no API key needed |
| `web_monitor` | Check if a site is up, measure response time, get HTTP headers |
| `html_to_markdown` | Convert any URL or HTML to clean markdown |
| `web_multi_extract` | Extract content from multiple URLs in parallel |
## Installation
### For Claude Code
Add to your Claude Code MCP settings (`~/.claude/settings.json`):
```json
{
"mcpServers": {
"web-tools": {
"command": "npx",
"args": ["@rog0x/mcp-web-tools"]
}
}
}
```
### For Claude Desktop
Add to `claude_desktop_config.json`:
```json
{
"mcpServers": {
"web-tools": {
"command": "npx",
"args": ["@rog0x/mcp-web-tools"]
}
}
}
```
### Manual Installation
```bash
npm install -g @rog0x/mcp-web-tools
mcp-web-tools
```
## Usage Examples
### Extract content from a webpage
```
Use web_extract to get the main content from https://example.com
```
### Search the web
```
Use web_search to find "best TypeScript frameworks 2026"
```
### Monitor a website
```
Use web_monitor to check if https://api.example.com is responding
```
### Convert page to markdown
```
Use html_to_markdown to convert https://docs.example.com/guide to readable markdown
```
### Batch extraction
```
Use web_multi_extract to get content from these URLs: [url1, url2, url3]
```
## Features
- **No API keys required** — uses DuckDuckGo for search, direct HTTP for everything else
- **Fast** — parallel extraction, 15s timeout per request
- **Clean output** — strips scripts, styles, ads; extracts meaningful content
- **Lightweight** — minimal dependencies, no headless browser needed
- **Production-ready** — proper error handling, timeouts, input validation
## Requirements
- Node.js 18+
## License
MIT — rog0x
TDQS
Scored across 5 tools
web_extract and web_multi_extract are clearly related, with the latter being just a parallel variant, and html_to_markdown overlaps with web_extract for URL-to-content conversion. Search and monitor are clearly distinct, but the extraction/convert boundary could cause misselection.
Most tools follow web_<action>, but html_to_markdown breaks the prefix pattern and uses a different target_to_target style. The pair web_extract/web_multi_extract is consistent, but overall naming conventions are mixed.
Five tools is a well-scoped size for a web utility server, covering search, monitoring, extraction, and conversion without unnecessary bloat. Each tool earns its place, though the single vs. multi extract duplication is minor.
The toolkit covers core web operations: search, availability/response checking, single-URL and multi-URL extraction, and HTML-to-markdown conversion. Minor gaps exist (e.g., no URL validation or site traversal), but agents can accomplish common web tasks without dead ends.