# August 2025

## Power your AI client with our MCP Server

What if you could use your AI client as a personal agent that scrapes websites and retrieves the data for you? Well, ScraperAPI's MCP server makes that possible! It connects your LLM to ScraperAPI and enables you to scrape the web simply by prompting.

### <mark style="background-color:blue;">Installation</mark>

Install the **`scraperapi-mcp-server`** using pip:

```bash
pip install scraperapi-mcp-server
```

### <mark style="background-color:blue;">Setup (Claude Desktop App)</mark>

1. Open Claude Desktop Application
2. Access the Settings Menu
3. Click on the settings icon (typically a gear or three dots in the upper right corner)
4. Select the "Developer" tab
5. Click on "Edit Config" and paste the JSON block below in the configuration file.

**Python**

```
{
  "mcpServers": {
    "ScraperAPI": {
      "command": "python",
      "args": ["-m", "scraperapi_mcp_server"],
      "env": {
        "API_KEY": "<YOUR_SCRAPERAPI_API_KEY>"
      }
    }
  }
}
```

**Docker**

```
{
  "mcpServers": {
    "ScraperAPI": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "-e",
        "API_KEY=${YOUR_SCRAPERAPI_API_KEY}",
        "--rm",
        "scraperapi-mcp-server"]
    }
  }
}
```

**That's it!** The MCP Server is now configured and is powering your AI Client. It starts automatically  when the keyword **`scrape`** is used in a prompt.

Check out the full guide with prompt examples below:

<a href="/pages/hmnvNsfSYaVElw2V1aNE" class="button primary" data-icon="hand-back-point-right">MCP Server docs</a>


---

# 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/resources/release-notes/august-2025.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.