Three tools, lean context
MCP ~1.4k tokens. Agent Skill ~110 idle tokens.
Start keyless. Fuse sources with RRF. Run deep research through one retrieval layer.
Requires Node.js >= 24.15. Install the CLI and try web search, library docs, and URL-to-Markdown extraction:
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.fetchFor Claude Code, Codex, Claude Desktop, or Cursor, add this MCP config. Omit env when using only zero-key sources:
{
"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"
}
}
}
}| Capability | 4–5 vendor MCPs | BYOK 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 start | Keys required | Keys required | Public HTML only | Six keyless source types + optional BYOK |
| Multi-engine fusion | Manual merging | One engine per call | No API provenance | URL deduplication + RRF + provenance |
| Multi-key failover | None | One key per source | IP rate limits | 32 keys/provider, 429 cooldown, 402 skip |
| URL credit protection | Paid scraper per fetch | Vendor scrape API | Basic HTML extraction | Defuddle first + ordered routing + challenge detection |
| Research beyond 60s | stdio timeout | Blocking calls time out | Not supported | Detached run / get / read / cancel jobs |