novada
One MCP server. All web data. Search, scrape, crawl, proxy, and AI research — in a single npx command.
The Problem
AI agents need web data but the tools are fragmented:
- Tavily does search but can't scrape or proxy
- Firecrawl does scrape but can't search or proxy
- BrightData does everything but ships 69 tools that bloat your context window
- Building it yourself means maintaining proxies, anti-bot bypass, retry logic, and 10 different APIs
The Fix
npx novada-mcp
One server. One API key. Tools that cover every web data need an AI agent has:
| Need | Tool | What it does |
|---|
| Find information | novada_search | Web search across Google, Bing, DuckDuckGo, Yandex, Yahoo |
| Read a page | novada_extract | Any URL → clean markdown, batch up to 10 in parallel |
| Deep research | novada_research | One call → parallel searches → dedup → cited multi-source report |
| Crawl a site | novada_crawl | BFS/DFS up to 20 pages with regex path filtering |
| Discover URLs | novada_map | Sitemap + BFS discovery without reading content |
| Platform data | novada_scrape | Amazon, LinkedIn, TikTok, GitHub, Zillow — 129 platforms |
| Monitor changes | novada_monitor | Track price/content/availability changes between checks |
| Verify claims | novada_verify | Parallel fact-checking against live web sources |
| Raw HTML | novada_unblock | JS render or full browser CDP for bot-protected pages |
| Browser automation | novada_browser | Navigate, click, type, fill forms, screenshot in cloud browser |
| Browser flows | novada_browser_flow | Multi-step browser automation sequences |
| Proxy credentials | novada_proxy | Residential, mobile, ISP, datacenter, static, dedicated — 195 countries |
| AI brand monitoring | novada_ai_monitor | Check how ChatGPT, Perplexity, Grok, Claude, Gemini mention your brand |
| Health check | novada_health | Check which API products are active on your key |
| Async scraping | novada_scraper_submit | Submit async scraping task → poll → retrieve results |
What Makes This Different
novada_research is unique. No other MCP server turns one question into a cited multi-source report. It searches across Google, Bing, and DuckDuckGo in parallel, deduplicates, extracts full content from the top 5 sources, and synthesizes with citations. One tool call replaces an entire research workflow. Depth options: quick (3 queries), deep (5-6), comprehensive (8-10).
Auto-escalation handles anti-bot automatically. Static fetch → JS render → Browser CDP. Known hard targets (Amazon, LinkedIn, G2, Zillow, Glassdoor, Walmart, Instagram, TikTok, Shein) skip straight to the right method based on a 30+ domain registry. You never think about Cloudflare, DataDome, Kasada, or PerimeterX — the tool handles it.
Agent-first design (8.5/10 benchmark score). Every response includes agent_instruction with structured next-step guidance, source field (live/cache/wayback), structured errors with failure_class, cross-tool hints suggesting better alternatives, and a ## Agent Action block with machine-parseable status codes.
Quick Start
-
Get a key at novada.com
-
Add to your MCP client:
Claude Code:
claude mcp add novada -e NOVADA_API_KEY=your_key -- npx -y novada-mcp
Claude Desktop / Cursor / VS Code / Windsurf:
{
"mcpServers": {
"novada": {
"command": "npx",
"args": ["-y", "novada-mcp"],
"env": { "NOVADA_API_KEY": "your_key" }
}
}
}
- Try it:
novada_search({query: "Claude MCP tutorials", num: 5})
novada_research({question: "How do MCP servers work?", depth: "deep"})
novada_extract({url: "https://news.ycombinator.com", format: "markdown"})
novada_monitor({url: "https://amazon.com/dp/B09...", fields: ["price", "availability"]})
Tool Reference
Search & Research
| Tool | Purpose | Key Params | Example |
|---|
novada_search | Web search via 5 engines | query, engine, num, time_range, include_domains | novada_search({query: "best API gateways 2026", engine: "google", num: 10}) |
novada_research | Multi-source parallel research | question, depth, focus | novada_research({question: "Kong vs Traefik vs APISIX", depth: "comprehensive", focus: "performance benchmarks"}) |
novada_verify | Fact-check claims against web | claim | novada_verify({claim: "GPT-5 was released in 2026"}) |
Extract & Crawl
