← Back to Index
Luban MCP (Snapmaker Ray)VerificationConfidence: Low

Every Luban MCP motion guard refuses while headPower > 0 or headStatus is on, but on the Snapmaker Ray the firmware sets the laser power reading to 0 at init and never writes it, and no SACP channel sets headStatus. The guards therefore always pass on the Ray whatever the laser is doing, and results imply the toolhead is off. Safety-relevant: the agent can move a firing laser believing it is off.

Impact Analysis

Persona
Hardware Engineer
Team Size Impact
5x Multiplier
Prototype Delay
3 Days
Est. Annual Cost
$30,000
  • 1 user · 1 month240 min
  • Rest of team960 min
  • Rest of year13,200 min

monthly_minutes × 12 × team_multiplier ÷ 60 × $75/hr = $30k/yr

$75/hr assumed rate.

Annual team-minutes decomposed from the reported monthly inputs.

Evidence & Sources

1 Sources
tyeth/Luban issue #316: MCP: Ray laser-off guard reads a power value the firmware never sends
github.com
→

Analyst Notes

From the Grok ProductFlo pain-radar digest, Oct 19 2026. Verified live 2026-10-19: issue text confirms the firmware never writes the power value the guard reads. Cost model assumes a ruined workpiece or a safety incident from motion under a live laser.