kicad-mcp-pro (KiCad MCP bridge)ECADConfidence: Medium

A KiCad MCP bridge normalizes DRC, connectivity, and geometry into its own output format, and that normalized output can silently disagree with the native KiCad engine. The maintainer had to build seeded false-PASS and false-FAIL tests because the bridge layer cannot be trusted as engineering truth on its own.

Impact Analysis

Persona

Electrical Engineer

Team Size Impact

5x Multiplier

Prototype Delay

2 Days

Est. Annual Cost

$18,000

1 user · 1 month240 min
Rest of team960 min
Rest of year13,200 min

monthly_minutes × 12 × team_multiplier ÷ 60 × $75/hr = $18k/yr

$75/hr assumed rate.

Annual team-minutes decomposed from the reported monthly inputs.

Evidence & Sources

1 Sources

kicad-mcp-pro PR #1126: eval harness comparing MCP DRC normalization against native KiCad engine output

github.com

→

Analyst Notes

From the 2026-10-07 pain-radar digest (finding 1): the most sophisticated open-source KiCad agent bridge spends its CI budget proving its own layer agrees with the native engine. Evidence is strong that the failure class is real (seeded divergence tests), though no specific shipped-board incident is attached. Cost model assumes engineers re-verify suspect agent-reported DRC results by hand.