# What is Model Context Protocol (MCP), and how does it benefit Web Scraper API usage?

Model Context Protocol (MCP) is a standardized framework that establishes secure two-way connections between AI models and web data sources.

🛠️ The process transforms raw HTML into formats that LLMs can immediately understand.

MCP allows LLMs to access web data obtained with [Web Scraper API](https://oxylabs.io/products/scraper-api/web). Before MCP, integrating LLMs with web data required custom implementations for each source, leading to complex and hard-to-scale solutions.

#### Customization capabilities <a href="#h_227274958d" id="h_227274958d"></a>

* Tailor metadata parameters to match specific requirements.
* Configure custom instructions and disclaimers.
* Adjust context handling based on your LLM's processing needs.

🧠 See our [documentation](https://developers.oxylabs.io/scraper-apis/web-scraper-api/solutions-for-ai-workflows/model-context-protocol-mcp) and [GitHub](https://github.com/oxylabs/oxylabs-mcp) for specific steps to enable MCP for your projects.