
MarkUDown
Web scraping for AI agents: scrape, crawl, search and extract any site as clean Markdown or JSON.
- GitHub stars
- 16
- tools
- 10
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Nov 16, 2026
Tools
10 toolsPublic tool metadata for what this MCP can expose to an agent.
scrapeScrape a single URL and return its content as clean Markdown.
Scrape a single URL and return its content as clean Markdown.
No parameter schema in public metadata yet.
mapDiscover all URLs on a website via sitemap parsing and link crawling.
Discover all URLs on a website via sitemap parsing and link crawling.
No parameter schema in public metadata yet.
crawlRecursively crawl a website, following internal links. Returns Markdown for each page.
Recursively crawl a website, following internal links. Returns Markdown for each page.
No parameter schema in public metadata yet.
searchRun a Google search and optionally scrape the full content of each result page.
Run a Google search and optionally scrape the full content of each result page.
No parameter schema in public metadata yet.
extractScrape a URL and extract structured data using a natural language prompt.
Scrape a URL and extract structured data using a natural language prompt.
No parameter schema in public metadata yet.
batch_scrapeScrape multiple URLs in parallel. Returns Markdown for each.
Scrape multiple URLs in parallel. Returns Markdown for each.
No parameter schema in public metadata yet.
screenshotTake a full-page screenshot of a URL.
Take a full-page screenshot of a URL.
No parameter schema in public metadata yet.
deep_researchScrape multiple URLs and synthesize their content into a comprehensive research report using an LLM.
Scrape multiple URLs and synthesize their content into a comprehensive research report using an LLM.
No parameter schema in public metadata yet.
agentLaunch an AI agent that autonomously navigates a website to answer a question or complete a task.
Launch an AI agent that autonomously navigates a website to answer a question or complete a task.
No parameter schema in public metadata yet.
change_detectionDetect whether a URL's content has changed since it was last checked.
Detect whether a URL's content has changed since it was last checked.
No parameter schema in public metadata yet.
Sponsors
Configuration
MARKUDOWN_API_KEY*secretMarkUDown API key. Get one free (500 credits, no card) at https://scrapetechnology.com/markudown/register
Readme
markudown-mcp
MCP server for MarkUDown / Scrape Technology — gives AI agents (Claude, Cursor, Windsurf, n8n, LangGraph, etc.) access to web scraping, Google search, data extraction, and more.
No infrastructure needed. Just an API key — get one free at scrapetechnology.com/markudown/register (500 free credits, no credit card). Docs: scrapetechnology.com/markudown/docs.
MARKUDOWN_API_KEY=your-key npx -y markudown-mcp
How it works
AI Agent (Claude Desktop, Cursor, etc.)
│ MCP protocol (stdio)
▼
markudown-mcp (this package)
│ HTTPS + polling
▼
api.scrapetechnology.com
│ BullMQ jobs
▼
MarkUDown Engine workers
Quick start
MARKUDOWN_API_KEY=your-key npx markudown-mcp
Details
- Repository
- github.com/scrape-technology/markudown-mcp
- Website
- scrapetechnology.com/markudown
- Categories
- Documents & Knowledge, Search & Web Crawling, Data & Analytics
- Package
markudown-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active