The MCP Server Fetch Python is a web content extraction and transformation server that provides tools for fetching, rendering, and converting web content into various formats:
Extract raw text: Directly fetch raw text from URLs, ideal for structured data formats like JSON, XML, CSV, TSV, or plain text
Fetch rendered HTML: Retrieve fully rendered HTML content including JavaScript-generated elements, essential for modern web applications and SPAs
Convert to Markdown: Transform web page content into clean, well-formatted Markdown while preserving structural elements
Extract content from media: Use AI-powered tools to analyze images and videos, converting visual content into Markdown format using computer vision and OCR (requires an OpenAI API key)
Enables fetching content from JavaScript-rendered pages through a headless browser, making it possible to extract content from modern web applications and SPAs
Converts web page content to well-formatted Markdown while preserving structural elements like tables and definition lists
Leverages OpenAI's vision capabilities for AI-powered content extraction from media files (images and videos) when provided with an API key
Supports extraction of raw text content from XML files through the get-raw-text tool for direct access to structured data
mcp-server-fetch-python
An MCP server for fetching and transforming web content into various formats. This server provides comprehensive tools for extracting content from web pages, including support for JavaScript-rendered content and media files.
Features
Tools
The server provides four specialized tools:
get-raw-text: Extracts raw text content directly from URLs without browser rendering
Arguments:
url: URL of the target web page (text, JSON, XML, csv, tsv, etc.) (required)
Best used for structured data formats or when fast, direct access is needed
get-rendered-html: Fetches fully rendered HTML content using a headless browser
Arguments:
url: URL of the target web page (required)
Essential for modern web applications and SPAs that require JavaScript rendering
get-markdown: Converts web page content to well-formatted Markdown
Arguments:
url: URL of the target web page (required)
Preserves structural elements while providing clean, readable text output
get-markdown-from-media: Performs AI-powered content extraction from media files
Arguments:
url: URL of the target media file (images, videos) (required)
Utilizes computer vision and OCR for visual content analysis
Requires a valid OPENAI_API_KEY to be set in environment variables
Will return an error message if the API key is not set or if there are issues processing the media file
Related MCP server: mcp-server-collector
Usage
Claude Desktop
To use with Claude Desktop, add the server configuration:
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Environment Variables
The following environment variables can be configured:
OPENAI_API_KEY: Required for using the
get-markdown-from-mediatool. This key is needed for AI-powered image analysis and content extraction.PYTHONIOENCODING: Set to "utf-8" if you encounter character encoding issues in the output.
MODEL_NAME: Specifies the model name to use. Defaults to "gpt-4o".
Local Installation
Alternatively, you can install and run the server locally:
Then add the following configuration to Claude Desktop config file:
Development
Debugging
You can start the MCP Inspector using npxwith the following commands: