Mmcp.market

TypeUI MCP server

by bergside·io.github.bergside/typeui·v1.0.1

Design systems, UI prompts, and layout variations for AI coding tools.

A93/100grade A
What users say
No reviews yet
Be the first
Safety scan
A93/100

full report

Adoption
Established

2.0k stars

Reviews

Write one

Nobody has reviewed TypeUI yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

TypeUI tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 500ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityOAuth resource metadata advertised on 40115/15
  • Maintenancelast push 85 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 93/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the TypeUI repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.bergside/typeui -->

TypeUI - Build better UI with AI

TypeUI is an AI-first platform where you can use design skills, UI prompts, and other resources to enhance AI capabilities to generate better user interfaces and design when building websites and applications. The resources from this repository will work with any AI provider, given they support markdown files or general prompting.

Getting started

Install TypeUI where you build. Connect your AI coding tool to TypeUI MCP, then ask for UI in plain language while TypeUI supplies design systems, prompts, and layout variation guidance.

Codex Connect Codex to TypeUI MCP automatically with the TypeUI Codex plugin. Install in Codex → Claude Give Claude access to curated design guidance while it writes or refactors UI. Install in Claude → Cursor Use the TypeUI Cursor plugin while Cursor builds screens, sections, and variations. Install in Cursor → Grok Add the hosted TypeUI MCP server to Grok. Open Grok guide → Z.ai Add the hosted TypeUI MCP server to Z.ai ZCode. Open Z.ai guide → Hermes Install the TypeUI MCP plugin for Hermes Agent. Open Hermes guide → OpenClaw Add the hosted TypeUI MCP server to OpenClaw. Open OpenClaw guide → <img src="./ai-tools-logos/light/eve.svg"

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

claude mcp add --transport http typeui https://mcp.typeui.sh/mcp
Add to Cursor

TypeUI: common questions

Is TypeUI MCP server safe?
Yes, by our scan: it is graded A (93/100). Read the TypeUI safety report
How do I install TypeUI?
It runs remotely at mcp.typeui.sh. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
Does TypeUI need an API key?
No key to paste: it signs you in with OAuth when your client connects.
Is TypeUI maintained?
The last commit was 85 days ago (2026-07-04). The latest release is v1.0.1.
Is TypeUI up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of TypeUI?
Servers from other publishers that do the same job: Raven MCP server, melta UI MCP server and memi MCP server. Compare all TypeUI alternatives.

Alternatives to TypeUI

Same job from other publishers: the closest match first, then the best rated.

All TypeUI alternatives →
  • Raven
    Design intelligence for coding agents: audits, design systems, and a taste profile agents consult.
    B
  • melta UI
    AI-Ready design system MCP: melta UI tokens, component contracts, 99 rules, check_html self-verify
    A
  • memi
    Memi is the read-only design engineering audit and skill layer for coding agents.
    A
  • Buoy
    Design tokens and drift checks for coding agents: use the token, not the hardcoded value.
    A
  • Mimic AI
    Builds Figma from your design system: real components and tokens, enforced, learning every build.
    A

More from bergside →