Skrape MCP Server
[](https://smithery.ai/server/@skrapeai/skrape-mcp)
Convert any webpage into clean, LLM-ready Markdown using [skrape.ai](https://skrape.ai). Perfect for feeding web content into LLMs.
This MCP server provides a simple interface to convert web pages to structured, clean Markdown format using the skrape.ai API. It's designed to work seamlessly with Claude Desktop, other LLMs, and MCP-compatible applications.
Why Use Skrape for LLM Integration?
- **Clean, Structured Output**: Generates well-formatted Markdown that's ideal for LLM consumption
- **Noise Reduction**: Automatically removes ads, navigation menus, and other irrelevant content
- **Consistent Format**: Ensures web content is uniformly structured regardless of the source
- **JavaScript Support**: Handles dynamic content by rendering JavaScript before conversion
- **LLM-Optimized**: Perfect for feeding web content into LLMs like Claude, GPT, and other LLM models
Features
Tools
- `get_markdown` - Convert any webpage to LLM-ready Markdown - Takes any input URL and optional parameters - Returns clean, structured Markdown optimized for LLM consumption - Supports JavaScript rendering for dynamic content - Optional JSON response format for advanced integrations
Installation
Installing via Smithery
To install Skrape MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@skrapeai/skrape-mcp):
Manual Installation
- Get your API key from [skrape.ai](https://skrape.ai)
- Install dependencies:
- Build the server:
- Add the server config to Claude Desktop:
On MacOS:
On Windows:
Add this configuration (replace paths and API key with your values):
Using with LLMs
Here's how to use the server with Claude or other LLM models:
- First, ensure the server is properly configured in your LLM application
- Then, you can ask the ALLMI to fetch and process any webpage:
The resulting Markdown will be clean, structured, and ready for LLM processing.
Advanced Options
The `get_markdown` tool accepts these parameters:
- `url` (required): Any webpage URL to convert
- `returnJson` (optional): Set to `true` to get the full JSON response instead of just markdown
- `options` (optional): Additional scraping options - `renderJs`: Whether to render JavaScript before scraping (default: true)
Example with all options:
Development
For development with auto-rebuild:
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector):
The Inspector will provide a URL to access debugging tools in your browser.