Rubric

UX指南、研究和审计检查清单,适用于编码代理,以及您自己的Rubric审计报告和分析。远程服务器,支持OAuth:claude mcp add --transport http rubric https://rubric.design/mcp

托管 MCP 服务器

npx add-mcp 'https://rubric.design/mcp'

可安装到 Claude Code、Codex、Cursor 等客户端

文档

Rubric

Curated UX knowledge, served to coding agents over MCP.

Rubric answers two questions: what should I build (design-time guidelines) and what is wrong with this page (an audit checklist an agent runs, then submits its observations against). Findings carry severity, impact, concrete actions and citations. There are no scores — severity is the only ranking signal, judged once per unit rather than computed per site.

Connect

Endpoint: https://rubric.design/mcp — streamable HTTP, nothing to install.

Two ways in:

There is no unauthenticated access and no shared demo key.

Tools

toolwhat it doesfree tier returns
search_ux_knowledgeFind units by query and facets.title, guideline
get_guidelinesDesign-time prescriptions for a surface or discipline.guideline
get_checklistWhat to check on a page, with navigation hints.everything
get_findingsThe written finding for a unit and outcome.issue, severity
create_auditStart an audit of a URL.—
submit_findingsRecord what the agent judged, unit by unit.—
get_reportRead an audit back, as JSON or markdown.issue, severity

A paid call adds the impact, the actions and the references.

Limits

Free calls are capped per day, per account, by call count. A paid plan includes a monthly allowance of MCP calls. An audit from your own agent uses no runs: runs are spent only by managed runs on Rubric's browser. Plans are at https://rubric.design/app/plan. Connecting an account grants nothing on its own.

Machine-readable