Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.pluxx.dev/llms.txt

Use this file to discover all available pages before exploring further.

This page groups three common MCP import patterns:
  • large tool surfaces that need taxonomy refinement
  • live commercial MCPs with product-shaped workflow grouping
  • authenticated imports that use custom headers

​
Firecrawl-style

If your MCP has many granular tools, start with deterministic import and then run taxonomy refinement: 
npx @orchid-labs/pluxx init --from-mcp "npx -y @mendable/firecrawl-mcp" --yes
npx @orchid-labs/pluxx doctor
npx @orchid-labs/pluxx lint
npx @orchid-labs/pluxx agent prepare --website https://www.firecrawl.dev --docs https://docs.firecrawl.dev/mcp-server/introduction
npx @orchid-labs/pluxx agent run taxonomy --runner codex
Repository example: example/firecrawl-plugin Use this pattern when the first import is valid but too lexical or too fragmented.

​
Sumble-style

Use a live commercial MCP when you want a proof-quality example with real auth and workflow grouping. Full walkthrough: Typical commands: 
SUMBLE_API_KEY=... npx @orchid-labs/pluxx init \
  --from-mcp https://mcp.sumble.com \
  --yes \
  --auth-env SUMBLE_API_KEY \
  --auth-type bearer \
  --grouping workflow

​
PlayKit-style

Use custom header auth during import: 
npx @orchid-labs/pluxx init \
  --from-mcp https://mcp.playkit.sh/mcp \
  --yes \
  --auth-env PLAYKIT_API_KEY \
  --auth-type header \
  --auth-header X-API-Key \
  --auth-template '${value}'
Use this pattern when the provider expects an API key in a header other than Authorization.

​
Which example to start from

  • choose Firecrawl-style when the tool surface is large and needs semantic cleanup
  • choose Sumble-style when you want a high-signal live MCP example with workflow grouping
  • choose PlayKit-style when the main complication is authenticated import via a custom header