Design-intelligent MCP server for Figma. 201 design-intelligent tools for Figma. Every tool knows typography, spacing, color, accessibility. Not a shape proxy — a design engine.
conductor-figma has 6 tools with basic schemas and descriptions, but significant quality gaps. Tool names lack consistent verb prefixes (e.g., 'suggest_color_palette' vs 'get_design_craft_guide'). Descriptions are present but generic (avg ~80 chars, below 194-char baseline). Input schemas exist but lack depth: most parameters have minimal descriptions, no enums for constrained inputs (e.g., 'mode' in suggest_color_palette accepts 'dark'|'light' but this is not formalized), and no output schemas documented. Error handling is minimal, handlers catch exceptions but provide no recovery guidance. The 'design_from_prompt' tool is destructive (WRITE risk) but has no confirmation pattern or dry-run option. No tool annotations (readOnlyHint/destructiveHint) despite clear read/write distinction.
Checks WCAG contrast ratio between foreground and background colors
Generates complete Figma design from natural language prompt
Returns design craft guide with typography, spacing, color, and accessibility best practices
Interprets design prompt and returns structured interpretation summary
Generates semantic color palette from brand color
Generates typographic scale from base size and ratio
No output schemas documented. Tools return text or JSON but LLMs cannot predict structure for downstream chaining.
Constrained inputs not formalized as enums. 'mode' in suggest_color_palette accepts 'dark'|'light' but schema shows type:string with no enum constraint. LLMs may hallucinate invalid values.
Destructive tool 'design_from_prompt' (WRITE risk) lacks confirmation or dry-run pattern. No recovery guidance if agent makes mistake.
Parameter descriptions are minimal (avg ~30 chars). 'brandColor' and 'baseSize' lack format/range guidance. LLMs cannot validate inputs before calling.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 41 | <=2025-11-25 | v2 |
No tool annotations (readOnlyHint/destructiveHint). Server declares risk levels but does not expose them in tool definitions for client awareness.