# MCP Server The **ScraperAPI MCP Server** connects your LLM to ScraperAPI, making scraping as easy as writing a prompt. It is designed to run as a local server on your machine. The LLM client automatically launches it once it is configured. ## How It Works * **Runs locally** (via Python or Docker). * Starts **automatically** when your client needs it. * Supports a range of **ScraperAPI parameters** (geotargeting, premium proxies, JS Rendering, etc.) * Uses **ScraperAPI's infrastructure** to scrape and fetch the data. * Delivers the response directly to your AI, ready to be processed as you decide. --- # 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/llm-integrations/mcp-server.md?ask= ``` 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.