Skip to content

nb-searchSearch, extract, research.

Start keyless. Fuse sources with RRF. Run deep research through one retrieval layer.

30-Second Zero-Key Quick Start ​

Requires Node.js >= 24.15. Install the CLI and try web search, library docs, and URL-to-Markdown extraction:

bash
npm install -g @nb-corp/nb-search

nb-search search "WebAssembly component model"
nb-search search "react useOptimistic" --lane context7.docs
nb-search fetch "https://nodejs.org/en/about/releases/" --pipeline direct.fetch

For Claude Code, Codex, Claude Desktop, or Cursor, add this MCP config. Omit env when using only zero-key sources:

json
{
  "mcpServers": {
    "nb-search": {
      "command": "npx",
      "args": ["-y", "--package=@nb-corp/nb-search", "nb-search-mcp"],
      "env": {
        "NB_SEARCH_TAVILY_API_KEY": "YOUR_API_KEY",
        "NB_SEARCH_EXA_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Why Not Stack Separate Vendor MCPs? ​

Capability4–5 vendor MCPsBYOK wrapper (mcp-omnisearch)Keyless scraper (open-webSearch)@nb-corp/nb-search
Context overhead~15k–35k tokens, 20+ tools~4k–8k tokens~1k–2k tokens~1.4k MCP / ~110 Skill tokens
Zero-key startKeys requiredKeys requiredPublic HTML onlySix keyless source types + optional BYOK
Multi-engine fusionManual mergingOne engine per callNo API provenanceURL deduplication + RRF + provenance
Multi-key failoverNoneOne key per sourceIP rate limits32 keys/provider, 429 cooldown, 402 skip
URL credit protectionPaid scraper per fetchVendor scrape APIBasic HTML extractionDefuddle first + ordered routing + challenge detection
Research beyond 60sstdio timeoutBlocking calls time outNot supportedDetached run / get / read / cancel jobs

Documentation & AI Index ​

Released under the MIT License · AI Index: /nb-search/llms.txt