Skrape MCP Server

What is Skrape MCP Server?

Skrape MCP Server converts any webpage into clean, LLM-ready Markdown using the skrape.ai API. It is designed for use with Claude Desktop, other LLMs, and MCP-compatible applications.

How to use Skrape MCP Server?

Install automatically via Smithery or manually: get an API key from skrape.ai, install dependencies (npm install), build (npm run build), then add the server configuration to your Claude Desktop config file. Invoke the get_markdown tool with a URL and optional parameters.

Key features of Skrape MCP Server

• Converts web pages to clean, structured Markdown
• Removes ads, navigation, and irrelevant content
• Supports JavaScript rendering for dynamic content
• Returns optional JSON response format
• Optimized for LLM consumption (Claude, GPT, etc.)

Use cases of Skrape MCP Server

• Feeding web content into LLMs for analysis or summarization
• Converting dynamic web pages into readable Markdown
• Extracting clean text from news articles or documentation
• Integrating web scraping into MCP‑compatible AI assistants

FAQ from Skrape MCP Server

What is the main tool provided?

The server exposes a single tool called get_markdown, which takes a URL and optional parameters to return clean Markdown from any webpage.

How do I get an API key?

You can get your API key from skrape.ai.

Does it support JavaScript rendering?

Yes, the get_markdown tool supports JavaScript rendering (enabled by default) to handle dynamic content.

What optional parameters are available?

You can set returnJson to true to get the full JSON response instead of just Markdown, and in the options object you can set renderJs to false to disable JavaScript rendering.

How do I install it for Claude Desktop?

You can install automatically via Smithery with the command npx -y @smithery/cli install @skrapeai/skrape-mcp --client claude, or manually by adding the server configuration to your Claude Desktop config file (path varies by OS).