Novada MCP

One MCP server for all web data. Scrape, search, crawl, and AI research in one install.

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)

Claude Code

claude mcp add --transport http novada-mcp 'https://mcp.novada.com/mcp' --header 'Authorization: <Bearer <NOVADA_API_KEY>>'

JSON configuration (Claude Desktop, Cursor, VS Code)

{
    "mcpServers": {
        "novada-mcp": {
            "type": "http",
            "url": "https://mcp.novada.com/mcp",
            "headers": {
                "Authorization": "<Bearer <NOVADA_API_KEY>>"
            }
        }
    }
}

NPM package novada-mcp

Claude Code

claude mcp add novada-mcp -e 'NOVADA_API_KEY=<your novada_api_key>' -- npx -y novada-mcp@0.9.44

JSON configuration (Claude Desktop, Cursor, VS Code)

{
    "mcpServers": {
        "novada-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "novada-mcp@0.9.44"
            ],
            "env": {
                "NOVADA_API_KEY": "<your novada_api_key>"
            }
        }
    }
}

Environment variables

NOVADA_API_KEY required secret Your Novada API key from https://www.novada.com

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents

Novada MCP
Quickstart
Get your key
How to choose a tool
Why Novada
Repository layout
Links
License

Novada MCP

One MCP server for the entire live web. Search, extract, scrape, crawl, proxy, browser automation, and AI-powered research — behind a single hosted connection, or one local install if you'd rather run it yourself.

Quickstart · Get your key · How to choose a tool · Why Novada · Repository layout · Links


✅ Works with any MCP client — Claude, Cursor, Windsurf, VS Code, or `npx` locally	🎯 14 typed per-platform scrapers — Amazon, Google, LinkedIn, TikTok, … each a closed `operation` enum, so an agent can't call an invalid op
🎁 $10 free credits — no credit card needed — up to 1,000 calls/month	⚡ Hosted-first, zero install — point at one URL, or self-host in one command

Quickstart

Novada is hosted-first — there's nothing to install. Point your client at the hosted URL and you're done.

Security note: the hosted endpoint never accepts your API key as a URL query parameter or path segment — only an Authorization: Bearer <key> header, or OAuth sign-in, is accepted. This keeps the key out of URLs, server logs, proxies, and browser history. Never share your key or paste it into a URL.

claude.ai (web)

Go to Settings → Connectors → Add custom connector.
Name it Novada.
Paste the bare URL and sign in with your Novada account when prompted (OAuth):
```
 https://mcp.novada.com/mcp
```
Click Add.

Claude Code

claude mcp add --transport http novada https://mcp.novada.com/mcp --header "Authorization: Bearer YOUR_KEY"

Full per-client install (Cursor/Windsurf/VS Code + local self-host) → npm-package/README.md.

Try it

novada_setup()                                          — validates your key, shows balance
novada_search({query: "Claude MCP tutorials"})          — web search
novada_extract({url: "https://example.com"})            — read any URL
novada_research({question: "how do MCP servers work?"}) — parallel multi-source research

Get your key

Sign up at novada.com — no credit card required.
Copy your API key from novada.com.
You start with $10 in free credits, capped at 1,000 calls/month. Check what's left any time with novada_account({section: "balance"}) or novada_setup().

How to choose a tool

These are the tools you reach for most:

Tool	Use it when
`novada_setup`	First run — validate your key and see your balance. Start here.
`novada_search`	Find pages by query (google / duckduckgo / yandex; time, domain, geo filters).
`novada_extract`	Read one known URL — or up to 10 in parallel — through anti-bot pages.
`novada_research`	Answer a complex question — parallel multi-source search + extraction in one call.
`novada_scrape`	Structured records from 14 platforms (Amazon, LinkedIn, TikTok, …). Plus 14 typed per-platform tools — `novada_scrape_amazon`, `_google`, `_linkedin`, … — each a closed `operation` enum.
`novada_crawl`	Pull content from a bounded set of related pages (≤20) on one site.
`novada_map`	Discover what URLs exist on a site before fetching.
`novada_browser`	Interact with a page — click, type, screenshot, run JS.
`novada_proxy`	Route your own HTTP client through a specific IP type / country / session.

Not sure? Call novada_discover and it returns the full catalog with each tool's status.

📚 Full reference — all 37 tools →

37 tools across 6 categories. Self-host (npx novada-mcp) exposes all 37. The hosted default surface (mcp.novada.com) exposes 28 — the same registry minus 9 tools that don't apply to a stateless serverless endpoint: novada_browser / novada_browser_flow (both need a persistent CDP WebSocket session a serverless isolate can't hold), novada_site_copy (writes files to disk), novada_ip_whitelist / novada_static_ip_mgmt / novada_capture_apikey (write-gated account ops), novada_session_stats / novada_search_feedback (per-process in-memory state), and novada_verify — it is core-derived, not a hand-curated subset. Call novada_discover on your connection to see exactly what's available on it.

Where does it run?

Full local/hosted breakdown, all 37 tools

Tool	Local (`npx novada-mcp`)	Hosted (`mcp.novada.com`)
`novada_search`	✅	✅
`novada_extract`	✅	✅
`novada_crawl`	✅	✅
`novada_research`	✅	✅
`novada_map`	✅	✅
`novada_site_copy`	✅	❌ writes to local disk
`novada_search_feedback`	✅	❌ per-process in-memory state
`novada_scrape`	✅	✅
`novada_scrape_amazon` … `_perplexity` (14 platform tools)	✅	✅
`novada_ai_monitor`	✅	✅
`novada_monitor`	✅	✅
`novada_verify`	✅	❌ not on `novada_discover`'s hosted listing
`novada_proxy`	✅	✅
`novada_browser`	✅	❌ needs a persistent CDP WebSocket session
`novada_browser_flow`	✅	❌ needs a persistent browser session
`novada_account`	✅	✅
`novada_proxy_account_create`	✅	✅
`novada_proxy_account_list`	✅	✅
`novada_ip_whitelist`	✅	❌ write-gated account op
`novada_capture_apikey`	✅	❌ write-gated account op
`novada_static_ip_mgmt`	✅	❌ write-gated account op
`novada_discover`	✅	✅
`novada_setup`	✅	✅
`novada_session_stats`	✅	❌ per-process in-memory state

Full per-tool reference (same column) → docs/TOOLS.md.

Why Novada

14 dedicated per-platform scrapers. novada_scrape_amazon, _google, _bing, _duckduckgo, _yandex, _youtube, _instagram, _facebook, _tiktok, _x, _walmart, _linkedin, _github, _perplexity — each exposes a closed, typed operation enum scoped to that platform instead of the generic novada_scrape's open platform+operation string pair, so an agent can't guess an invalid operation for the wrong platform.
Honest tool surface. Every listed operation is verified-working — operations we can't currently deliver are marked and excluded, not left in to fail on you mid-task.
Contract-tested self-report. Tool descriptions are tested against actual behavior, not just written and forgotten — what a tool claims to return is checked against what it actually returns.
Drift-guarded tool registry. npm-package/src/tools/registry.ts is the single source of truth for the tool catalog; a test asserts the registered tools, the wired tools, and the novada_discover output can never diverge.
confirm:true write-gate. Every mutating tool (proxy sub-account creation, IP whitelist changes, static IP purchases, capture-key resets) requires an explicit two-step confirmation — no silent writes.
Callable onboarding. novada_discover and novada_setup are tools your agent can call itself to find the right tool or validate a key, without ever reading this README.

vs Firecrawl / Tavily (measured, not marketing):

4.9× more compact. An identical 5-result search query returned 2,761 bytes from Novada vs 13,421 bytes from Firecrawl — less agent token cost per answer.
Keyless to start. npx -y novada-mcp cold-starts with no key; novada_setup walks you to one only when a tool needs it.
Named anti-bot failures. On an unresolvable target, Novada's response names the exact blocker (e.g. anti_bot:kasada) instead of a generic error, so an agent can branch on it.

Repository layout

This is a monorepo with two artifacts:

npm-package/ — the novada-mcp npm package. Local stdio MCP server (npx novada-mcp); source of truth for all tool logic.
hosted-server/ — what runs at https://mcp.novada.com. An HTTP wrapper (auth, quota, rate-limit) on Vercel around the npm package's built output.

Full architecture map (entrances, dispatch core, where-does-X-live) → ARCHITECTURE.md; contributor routing → CONTRIBUTING.

License

MIT

Frequently asked questions

What is Novada MCP?

One MCP server for all web data. Scrape, search, crawl, and AI research in one install.

How do I install Novada MCP?

It runs as a remote server. In Claude Code: claude mcp add --transport http novada-mcp 'https://mcp.novada.com/mcp' --header 'Authorization: <Bearer <NOVADA_API_KEY>>'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Novada MCP need an API key?

Yes. It expects NOVADA_API_KEY, Authorization, which you set in its configuration.

Is Novada MCP open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains Novada MCP?

It is published by NovadaLabs. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.

Server details

Listed in: Official MCP Registry
Publisher: NovadaLabs
Category: Search and web
Runs: Remote + Local
GitHub stars: ★ 3
License: MIT
Language: TypeScript
Last commit: Oct 26, 2026
Open issues: 3
Version: 0.9.44
Published: Oct 26, 2026

io.github.NovadaLabs/novada-mcp

Similar servers

Agent Data Hub No-key live data for agents: FX, macro, weather, research, dev tools, task bundles, his...
Shop Nobi Search products from independent stores. Read-only remote MCP; no sign-in. Buy on merch...
Fortrip Search hotels worldwide, compare live room rates, and create booking payment links.
Geo402 Geo Web Fetch Read any public web page as seen from another country, as clean markdown. Pay per page.
Launchscene Real tech launch videos, scene by scene: search, see each scene, get timing to build yo...
TwexAPI Search X (Twitter) posts and read profiles, followers, trends and X Articles. OAuth sig...
DomainSpace Register .si and other domains, check availability and manage DNS from your AI agent.
OwnSearch Quality-ranked SearXNG search over MCP with local fleet state, scoring, and merged resu...

Search and web