Haunt API
Extract clean, structured data from any URL — directly from Claude, Cursor, or any MCP-compatible AI.
Haunt API MCP Server
Extract clean, structured data from any URL — directly from Claude, Cursor, or any MCP-compatible AI.
Quick Start
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on Mac):
{
"mcpServers": {
"haunt": {
"command": "npx",
"args": ["-y", "@hauntapi/mcp-server"],
"env": {
"HAUNT_API_KEY": "your-api-key"
}
}
}
}
Get a free API key at hauntapi.com — 100 requests/month, no credit card needed.
Tools
extract_url
Extract clean data from any URL. Handles JavaScript rendering and Cloudflare bypass automatically.
Extract the article content from https://example.com/blog/post
extract_batch
Extract from multiple URLs at once (up to 10).
Extract the title and price from these product pages: [url1, url2, url3]
extract_metadata
Pull metadata: title, description, Open Graph tags, Twitter cards, canonical URL.
Get the Open Graph metadata for https://example.com
Pricing
- Free: 100 requests/month
- Pro: $0.01/request (pay only for what you use)
Links
- API Docs: https://hauntapi.com/docs
- Get API Key: https://hauntapi.com
- GitHub: https://github.com/hauntapi/mcp-server
Related Servers
Bright Data
sponsorDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
transcriptor-mcp
An MCP server (stdio + HTTP/SSE) that fetches video transcripts/subtitles via yt-dlp, with pagination for large responses. Supports YouTube, Twitter/X, Instagram, TikTok, Twitch, Vimeo, Facebook, Bilibili, VK, Dailymotion. Whisper fallback — transcribes audio when subtitles are unavailable (local or OpenAI API). Works with Cursor and other MCP host
Selenium MCP Server
Control web browsers using the Selenium WebDriver for automation and testing.
CompanyScope MCP
Company intelligence in one tool call — funding, tech stack, employees, competitors, news from public APIs
Playwright MCP
Control a browser for automation and web scraping tasks using Playwright.
Olostep MCP Server
A server for web scraping, Google searches, and website URL lookups using the Olostep API.
Puppeteer Vision
Scrape webpages and convert them to markdown using Puppeteer. Features AI-driven interaction capabilities.
Render-fetch
Drop-in upgrade to Claude's WebFetch that auto-detects JS-rendered pages and fetches them with Playwright headless browser
ScraperCity
B2B lead generation MCP server - Apollo, Google Maps, email finder, skip trace, and 15+ more tools.
Conduit
Headless browser with SHA-256 hash-chained audit trails and Ed25519-signed proof bundles. MCP server for AI agents.
MCP URL2SNAP
A lightweight MCP server that captures screenshots of any URL and returns the image URL. Requires an AbstractAPI key.