mcp-native · quality-scored · real production code

Give your agent
41,113 real implementations

Semantic search over quality-scored components mined from real production repos — not a synthetic style guide. Connect Claude Code, Cursor, or Codex directly.

41,113
components indexed
37,187
with full source
16
categories
ai 3,949 ui 8,864 auth 2,885 database 2,454 payments 586 pos 1,319 crm 931 voice 1,076 email 348 infra 3,011 integration 3,055 automation 1,520 analytics 996 files 1,314 realtime 800 scraping 570

Why it's worth connecting

real production provenance

Every component is mined from an actual public repo, not generated on the fly — you get code that already works somewhere, with a GitHub permalink back to its source.

quality-scored, not guesswork

Each component carries 5 sub-scores (completeness, code quality, deployability, reusability, strategic value) rolled into one composite — filter by min_composite and only see the good stuff.

no context-switching

MCP-native means your agent searches this library from inside Claude Code, Cursor, or Codex directly — no separate browser tab, no copy-paste round trip.

scale a hand-curated kit can't match

40K+ real components across 16 categories — bigger and more varied than any single component library, because it's pulled from thousands of real codebases, not one.

How it works

step 1
Get a free API key below — no credit card, 10 searches/day.
step 2
Add it to your MCP client config (Claude Code, Cursor, Codex, etc):
{
  "mcpServers": {
    "cobalt-components": {
      "url": "https://15-204-92-178.nip.io/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}
step 3
Your agent can now call search_components, get_component, and library_stats directly — no copy-pasting code from a browser tab.

Free tier: 10 searches/day via MCP. No credit card.

Get a free API key