Skip to main content
Glama

extract_content

Extract and clean web page content into structured Markdown with citations, supporting multiple formats and image/link inclusion.

Instructions

Extract and clean content from a web page, returning Markdown with citation

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL to fetch and extract content from
formatNoOutput format (default: markdown)markdown
includeImagesNoWhether to include images in the output (default: true)
includeLinksNoWhether to include links in the output (default: true)
bypassRobotsNoWhether to bypass robots.txt restrictions (default: false)
useCacheNoWhether to use cached content if available (default: true)

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mukul975/mcp-web-scrape'

If you have feedback or need assistance with the MCP directory API, please join our Discord server