Primitiv
Related Servers
Alternatives to Primitiv
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to write AI-generated designs into design-tool canvases (MasterGo, Penpot) as native editable layers, and to read canvas selections back out as HTML + Tailwind, design tokens, and SVG assets. Runs locally with progressive tool disclosure and structurally truncated results so large design files stay within an agent's context budget.Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables AI coding agents to read the live state of an open Figma file — variables, modes, components, prototype edges and assets — and to export design tokens and code packages for web, iOS, Android, React, Django and Tauri through a user-run loopback bridge with separate read and write gates.2MIT
- AlicenseAqualityAmaintenanceEnables AI agents to score live URLs against a deterministic design contract, validate DTCG tokens and Lottie animations, audit accessibility, and retrieve design-system contracts, catalogs, and review rubrics.175 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to query a workspace's design system before writing UI and validate generated code against the same system afterward, using configurable token and component sources.13 npm1MIT
- AlicenseNot gradedqualityBmaintenanceProvides coding agents with local tools to inspect project UI inventories, propose and compare visual direction boards, compile versioned design contracts and DTCG tokens, retrieve section-specific blueprints, and audit running interfaces with browser evidence including screenshots, accessibility findings, and overflow measurements.MIT
- AlicenseAqualityBmaintenanceProvides deterministic, read-only design knowledge for AI coding agents to help them choose visual directions, plan UI states, and compose design tokens, all without network access.6416 npm4MIT
TDQS
Scored across 9 tools
Most tools have distinct purposes, but there are real overlaps: get_component vs get_component_context (both inspect a single component), and get_design_context vs get_component_catalog (both give a system overview). The descriptions mitigate this heavily with explicit cross-references ('for X, use Y instead'), keeping misselection risk low but nonzero.
Eight of nine tools use a clean get_<noun> pattern (get_component, get_token, get_conflicts, get_violations, get_inferred_rules, get_design_context, get_component_catalog, get_component_context). find_components is the lone deviation, but the search-vs-fetch distinction is meaningful and readable.
Nine tools is well-scoped for a read-only design-system inspection server. Each tool covers a distinct facet (catalog, discovery, component detail, tokens, rules, conflicts, violations, context) without redundancy in count.
The surface covers discovery, component lookup, token lookup, inferred rules, conflicts, and violations, giving broad lifecycle coverage for a read-only inspection role. Minor gaps exist (no explicit snapshot-compare or diagnostics tool outside get_design_context), but agents can work around these.