mukul975/mcp-web-scrape
View on GitHub โ๐ mcp-web-scrape โ Clean, cache-aware web content fetcher for AI agents. Fetch any URL โ extract readable content โ return Markdown/JSON with citations. โก Fast caching, ๐ค robots.txt compliant, ๐ Markdown-ready output, ๏ฟฝ๏ฟฝ works with ChatGPT/Claude Desktop.
36 โ
16 forksTypeScriptUpdated 6mo ago
What you need to know
MCP server for web scraping returning Markdown with citations, robot-aware fetching and ETag/304 caching, runnable via npx mcp-web-scrape@1.0.7.
Reviewed 2026-08-11
Topics
agentaiapicachechatgptcitationsclaudecontent-extractionllmmarkdownmcpmodel-context-protocolnodejsscraperssestdiotypescriptweb-crawlerweb-scraping
- Stars
- 36โ
- Forks
- 16
- Language
- TypeScript
- License
- MIT
- Created
- 2025-09-23
- Last push
- 2026-02-16