> For the complete documentation index, see [llms.txt](https://developers.oxylabs.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developers.oxylabs.io/help-center/pt-br/dados-para-llms/how-does-model-context-protocol-mcp-standardize-data-for-llms.md).

# Como o Model Context Protocol (MCP) padroniza dados para LLMs?

Saiba como o MCP oferece aos modelos de IA uma forma consistente de trabalhar com dados da web.

O Model Context Protocol (MCP) padroniza como modelos de IA se conectam a ferramentas e fontes de dados. As ferramentas são tipadas, com um nome definido e um conjunto de entradas, e qualquer cliente MCP pode chamá-las da mesma forma.

Com o servidor Oxylabs MCP para [API da Web](https://developers.oxylabs.io/products/web-api), seu modelo recebe as ferramentas de busca e raspagem neste formato. O conteúdo da página retorna como Markdown, ou como JSON quando você extrai campos específicos. Não há reformatação manual.

### **Como funciona**

* Conecte seu cliente MCP ao servidor MCP da Oxylabs para a Web API.
* Seu modelo chama as ferramentas de busca e raspagem conforme precisa delas.
* A Web API retorna os resultados como Markdown ou JSON.

🧠 Para configurá-lo, veja a [documentação do servidor MCP](https://developers.oxylabs.io/ai-workflows/mcp) e [GitHub](https://github.com/oxylabs/web-api-mcp).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://developers.oxylabs.io/help-center/pt-br/dados-para-llms/how-does-model-context-protocol-mcp-standardize-data-for-llms.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.