Rams: design review for UI code, inside your agent

Rams reviews UI code the way a design-literate senior engineer would: severity-rated findings with file and line, a 0–100 score, and a concrete fix for each issue. It runs as a hosted MCP server, so Claude Code, Cursor, Codex, and any MCP-capable agent can call it while they work, before the code is ever committed.

This repository is the connection guide. The engine is hosted. There is nothing to install or run locally.

Tools

The engine reviews React, Vue, Svelte, CSS, and SwiftUI against a rule set spanning accessibility, hierarchy, color, type, spacing, motion, and native-platform conventions. The live rule count is at rams.ai/rules.

Setup

Get a key at rams.ai (free tier included, no card).

Claude Code

claude mcp add --transport http rams https://worker.rams.ai/mcp --header "Authorization: Bearer rams_YOUR_KEY"

Cursor · .cursor/mcp.json

{
  "mcpServers": {
    "rams": {
      "url": "https://worker.rams.ai/mcp",
      "headers": { "Authorization": "Bearer rams_YOUR_KEY" }
    }
  }
}

Codex · ~/.codex/config.toml

[mcp_servers.rams]
url = "https://worker.rams.ai/mcp"
http_headers = { "Authorization" = "Bearer rams_YOUR_KEY" }

Any other MCP-capable agent: Streamable HTTP at https://worker.rams.ai/mcp with the key as a Bearer header (?apiKey= also works for gateways that can't set headers).

Then ask your agent:

rams review my changes

How it behaves

• Quick checks are built to run constantly while editing: after writing a component, after a refactor, before moving on.

• Full reviews are the commit-time artifact: the score you keep, the patches you apply.

• Criticals cap the score: one caps it at 59, two at 49, three or more at 39. A 90+ means something.

• Your code is reviewed and returned, never stored.

Elsewhere

• Web: rams.ai · Rules: rams.ai/rules · Pricing: rams.ai/pricing

• Official MCP registry: ai.rams/rams · Glama · Smithery · mcp.so

• GitHub App (reviews every PR automatically): rams.ai