Developer · Remote MCP server

Mlola UI

Mlola UI components, tokens and design rules for coding agents, with a markup checker.

Visit Mlola UI's website

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.mlolahq/mlola-ui
Version
1.6.1
Status
Active
Category
developer
Transport
Streamable HTTP, stdio (local process)
Package
npm
Published
2026-10-04
Updated
2026-10-04
Publisher
mlolahq (GitHub)
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/mlolahq) · how
Website
ui.mlola.com/docs/agents
Repository
github.com/mlolahq/mlola-ui (folder packages/cli)
Source
Registry API entry

Remote endpoints

TransportURLHeaders declared
Streamable HTTPhttps://ui.mlola.com/mcpNone

Live check

This directory connected to each remote endpoint and asked for its list of tools. The check connects and lists tools only; it doesn't run tools, sign in or test security.

Reachable
Yes (HTTP 200)
Handshake
mlola-ui 1.7.0 · protocol 2025-06-18
Tools discovered
6: get_design_rules, search_components, get_component, get_tokens, check_markup, get_install_command
Checked on
2026-10-05

How the live check works

Packages

RegistryPackageVersionTransportEnvironment variables
npmmlola-ui1.6.1stdioNone declared

How to connect Mlola UI

Mlola UI is a remote MCP server: there is nothing to install. Its endpoint is https://ui.mlola.com/mcp, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.

No headers are declared in the registry entry. If the server needs you to sign in, a client that supports MCP authorization opens the service's own sign-in page when it first connects.

It can also run locally from a Node.js package published to the npm registry: mlola-ui version 1.6.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx - the usual command is npx -y mlola-ui@1.6.1.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "mlola-ui": {
      "command": "npx",
      "args": [
        "-y",
        "mlola-ui@1.6.1"
      ]
    }
  }
}

Derived from the registry entry; the live check above only shows whether the endpoint answered. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More developer servers

All 5,152 →
ServerRunsEndpoint or package
MisterdevAutonomous LLM build orchestrator that plans, edits, and verifies code across languages.Local · stdioPyPI: misterdev
MisterSandFR Supabase MCP SelfhostedManage Supabase projects end to end across database, auth, storage, realtime, and migrations. Moni…Remote · HTTPLive check: ✗ no handshakeserver.smithery.ai
MitosArchitectural decision memory for LLM-native workflows - markdown for humans, a graph for agents.Local · stdioPyPI: mitos-adr
Mitre AttckMITRE ATT&CK MCP - STIX bundles from github.com/mitre/cti.Remote · HTTPLive check: ✓ handshakegateway.pipeworx.io
MM7 Company MCPMM7 public B2B MCP: 1C ITS/RRP, requisites, EDI, cloud trial (GRM/Fresh) for AI agents.Remote · HTTPLive check: ✓ handshakemcp.mm7.ru
Mne DocsMCP server for MNE-Python documentation, source code, GitHub issues, and forum.Local · stdionpm: mne-docs-mcp
MNE-MCPMNE-Python neurophysiology analysis (EEG, MEG, sEEG, ECoG, fNIRS) via the Model Context Protocol.Local · stdioPyPI: mne-mcp
MnemeMemory layer for AI coding assistants. Indexes git history + code, exposes via MCP.Local · stdionpm: mneme-ai