MCP tools

Search approved knowledge with deterministic BM25 ranking, source paths, excerpts, confidence, and explicit no-match output.

Score maintained positive and negative cases for retrieval, abstention, architecture, task completeness, and anti-slop behavior.

List or read approved architecture guidance.

List or read Figma and design-system guidance.

List or read maintained brand, asset, icon, presentation, licensing, and visual-accessibility modules.

List or read approved dashboard and UX patterns.

List or read usability-evaluation guidance and schemas.

Validate evidence-backed product intent, primary audiences, outcomes, tasks, data, states, assumptions, requirements, and generation readiness.

Validate visual polish, semantic tokens, responsive composition, states, motion, charts, evidence readiness, contrast, provenance, icons, and presentations.

Validate operational claims, source traceability, fallback and stale states, disconnected recovery, and history or export provenance.

Validate metrics, findings, chart decisions, value states, large collections, operational hierarchy, and answer-flow tasks.

Validate a product archetype, primary tasks, recovery states, narrow paths, sources, journeys, and cross-references.

Validate anonymous comparison methods, required stages, retained claim evidence, and attributable human or representative-user records.

Validate a structured review and derive candidates from unresolved severity 3 and 4 findings.

Scan a repository against deterministic architecture and anti-slop rules.

Run browser checks and capture runtime evidence.

Combine contract, audit, runtime, acceptance, and human evidence into one decision.

Combine required journey-profile reports into a release decision.

List explicitly enabled local benchmark IDs and effective capabilities without source roots.

Read a completed local benchmark summary without starting commands.