Vercel MCP Web Crawler
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Vercel MCP Web Crawler
This is a production-ready, ultra-lightweight Web Crawling Model Context Protocol (MCP) server. It is built with TypeScript and Next.js (App Router), specifically optimized for deployment on Vercel's Free Tier.
Features
No Heavy Headless Browsers: Uses
fetch,cheerio,linkedom,@mozilla/readability, andturndownfor lightweight and fast scraping.Vercel Free Tier Ready: Strict execution limits via
AbortController(4s timeout per request) and concurrency control withp-limit.MCP Server over HTTP: Fully compatible with remote HTTP/SSE Model Context Protocol endpoint standards using
@modelcontextprotocol/sdk.
Related MCP server: read-website-fast
Available Tools
scrape_page: Fetch URL and convert to clean Markdown. Fallbacks tohttps://r.jina.ai/<url>.crawl_domain: Recursively crawl same-domain internal links (max 10 pages).extract_metadata: Parse title, meta descriptions, OpenGraph tags, canonical links, and JSON-LD.search_and_crawl: Fetch web search results, isolate top target links, and concurrently scrape them.
Setup & Deployment
Deploy to Vercel: Push this repository to GitHub and import it into Vercel.
Environment: No environment variables are required.
Client Configuration
To connect Cursor, Windsurf, or Claude Code to your deployed MCP server, you can use the built-in MCP HTTP Client support. Some editors support providing a direct HTTP/SSE endpoint.
Claude Code / Cursor / Windsurf Configuration Snippet
In your MCP client configuration (e.g., mcp.json or .claude_code/config.json), use the sse transport:
{
"mcpServers": {
"vercel-web-crawler": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/client", "--url", "https://<your-vercel-domain>.vercel.app/api/mcp"],
"env": {}
}
}
}Note: Since standard MCP config uses local commands, you might need an SSE client adapter if your editor doesn't support direct URL configurations. Claude Desktop recently added standard Server-Sent Events (SSE) support or you can use mcp-proxy scripts to bridge stdin to SSE.
If your editor natively supports Remote SSE MCP Servers, just provide the endpoint:
SSE Endpoint: https://<your-vercel-domain>.vercel.app/api/mcp
This server cannot be deployed
Maintenance
Related MCP Connectors
Markdown scrape, site map, page metadata, screenshots, web search and PDF to text. Pay per call
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.
Pages, crawls and URL batches as clean Markdown and JSON for AI agents, with an Evidence Record.
Extract public webpages as Markdown, map sites, and run bounded crawl jobs. API key required.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables converting any URL or website into clean, LLM-ready Markdown, supporting single-page scraping and full-site crawling for AI agents.MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and LLM pipelines to fetch webpages or crawl sites, extract main content, and convert it to clean, token-efficient Markdown with preserved links. It supports configurable crawling depth, caching, robots.txt compliance, and optional chunking for downstream processing.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to fetch webpages and crawl sites, extract main content, and convert it into clean Markdown with preserved links for fast, token-efficient scraping.-
- AlicenseNot gradedqualityAmaintenanceEnables AI agents and LLM pipelines to fetch and crawl web pages, extract readable content, and convert it into clean Markdown with preserved links while minimizing token usage.MIT