# mcp MCP server

Reliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.

## Links
- Registry page: https://www.getdrio.com/mcp/ai-foura-mcp
- Repository: https://github.com/fouradata/mcp
- Website: https://foura.ai/mcp

## Install
- Command: `npx -y @fouradata/mcp`
- Endpoint: https://mcp.foura.ai/mcp
- Auth: Auth required by registry metadata

## Setup notes
- Package: Npm @fouradata/mcp v0.5.0
- Environment variable: FOURA_API_KEY (required; secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://mcp.foura.ai/mcp

## Tools
- foura_single (FourA - single HTTP request) - Send one HTTP request and return the response. Use it for static pages, JSON APIs, and server-rendered HTML. Set unblocker:true for targets that reject basic HTTP requests. Switch to foura_proxy if the response is blocked, and use foura_browser when the page needs JavaScript. Endpoint: https://mcp.foura.ai/mcp
- foura_proxy (FourA - HTTP request via rotating proxies) - Route an HTTP request through rotating proxies with automatic retry. Use it when foura_single is blocked or the target requires a specific exit country. The response includes the proxy ID that succeeded; reuse it with foura_single or foura_browser, or exclude it with ignoreProxies. Use foura_browser when the page needs JavaScript. Set exitCountries for a strict country allowlist. Endpoint: https://mcp.foura.ai/mcp
- foura_browser (FourA - full browser navigation) - Load a public URL in a full browser session. JavaScript runs, the DOM renders, and cookies come back with the response. Use it for single-page apps, lazy-loaded content, or supported browser challenges. For a protected page, call foura_proxy first and pass its returned proxy ID here to reuse that exit. Set unblocker:false when you want the page exactly as it loads. Endpoint: https://mcp.foura.ai/mcp
- foura_auto (FourA - auto (smart fetch, picks the method for you)) - Give it a public URL and get the content back. This is the default when you don't want to choose between HTTP, proxy rotation, and a full browser. On protected targets, or whenever HTTP 200 may still be a challenge or incomplete page, pass validate.data.accept with text unique to the real content. Auto makes bounded attempts and returns either validated content or a failure; it cannot guarantee a match. The response includes completion details and, by default, reusable session values for follow-up calls. Use a lower-level tool when you need direct control over HTTP, proxy selection, or browser navigation. Endpoint: https://mcp.foura.ai/mcp

## Resources
Not captured

## Prompts
- scrape_product_page - Scrape a product page Fetch an e-commerce product URL and extract structured product info as JSON (title, price, image, availability). Arguments: url
- extract_article - Extract an article Fetch a news/blog article URL and extract the main content (headline, author, body, date) stripped of nav/ads/footer. Arguments: url
- monitor_pricing - Monitor a price Fetch a pricing page and extract the current price; compare to a target if provided. Arguments: url, target_price
- check_endpoint_health - Check API endpoint health GET a URL through foura_single with strict validation and report whether it's reachable and responding correctly. Arguments: url, expected_text
- bulk_fetch_urls - Fetch a list of URLs in parallel Fetch multiple URLs concurrently and return each outcome. Retry blocked URLs through foura_proxy. Arguments: urls
- smart_fetch - Fetch a URL the smart way (auto) Fetch any URL with foura_auto - one call that picks the method (direct / proxy / browser), gets past common bot protection, and returns the content. Use when you just want the page and don't want to choose a tool. Arguments: url, must_contain, extract

## Metadata
- Owner: ai.foura
- Version: 0.5.0
- Runtime: Npm
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 13, 2026
- Source: https://registry.modelcontextprotocol.io