# MCP Server <--> n8n

This page explains how to use the ScraperAPI MCP (Model Context Protocol) Server inside your **n8n workflows**.

{% hint style="danger" %}
**Note:** this integration uses the same community node as the basic ScraperAPI API resource and therefore requires a self‑hosted n8n instance. If you haven't installed the node yet or configured your API key, follow the installation instructions on the [n8n Integration page](/integrations/automation-and-workflow-integrations/n8n-integration.md).
{% endhint %}

#### How it works <a href="#how-it-works" id="how-it-works"></a>

**MCP Workflow**

1. **Add an MCP Client node** to your workflow. This node uses n8n's MCP Client Tool to send requests to the ScraperAPI MCP server.
2. **Configure the client node:**

* Endpoint: <https://mcp.scraperapi.com/mcp>
* Server Transport: HTTP Streamable
* Authentication: Bearer Auth
* Credential for Bearer Auth: Enter your ScraperAPI API key as the Bearer Token.
* Tools to include: Select a tool from the list (scrape, google\_search, google\_shopping, etc.)

3. Configure any optional parameters (see available [Parameters](https://github.com/scraperapi/n8n-nodes-scraperapi-official/blob/master/README.md#parameters)).

<figure><img src="/files/tuezIW8nRegE9t1QbWDE" alt=""><figcaption></figcaption></figure>

#### Google Shopping Scraping Workflow

This example uses the ScraperAPI MCP Server inside n8n to scrape Google Shopping results, transform the output, and email the final results automatically.

* Add an **MCP Client node** - [configure it](#how-it-works) to connect to the **ScraperAPI MCP Server**.
* During configuration, choose the **google\_shopping** tool from the dropdown list.
* Add an **Edit Fields node** to clean up the JSON response.
* Add a **Convert to File node** to export the results to a JSON file.
* Add a **Send an Email node** to send the final JSON file as an email attachment.

The example below shows a complete workflow that scrapes Google Shopping results, formats them and sends them over an email.

<figure><img src="/files/mgc1seLlOPrDEAiIo9sx" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.scraperapi.com/integrations/automation-and-workflow-integrations/n8n-integration/mcp-server-less-than-greater-than-n8n.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.