# Web Scraper

Extracts clean text, structured data, and metadata from any website. Captures full-page screenshots to visualize web content. Performs Google searches to find relevant information across the web.

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y smithery mcp add aparajithn/agent-web-scraper-mcp

# Browse available tools
npx -y smithery tool list aparajithn/agent-web-scraper-mcp

# Get full schema for a tool
npx -y smithery tool get aparajithn/agent-web-scraper-mcp scrape_url

# Call a tool
npx -y smithery tool call aparajithn/agent-web-scraper-mcp scrape_url '{}'
```

## Direct MCP Connection

Endpoint: `https://agent-web-scraper-mcp--aparajithn.run.tools`

## Tools (6)

- `scrape_url` — Fetch a URL and extract clean text/markdown content (like readability).
- `scrape_structured` — Extract structured data from a URL using CSS selectors.
- `screenshot_url` — Take a screenshot of a URL.
- `extract_links` — Extract all links from a URL with their text.
- `extract_meta` — Extract metadata from a URL (title, description, OG tags, favicon, etc).
- `search_google` — Search Google and return results.

```bash
# Get full input/output schema for a tool
npx -y smithery tool get aparajithn/agent-web-scraper-mcp <tool-name>
```