Index / MCP servers / Mlola UI

Mlola UI MCP server

Mlola UI is a remote MCP server that gives an AI agent 9 tools, among them check_markup, check_render, get_component. It answers at https://ui.mlola.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 3 of 4 times since 27 September 2026; the last check, on 12 November 2026, succeeded.

Status
Answering
Tools
9
Reliability
3 of 4 checks
Response time
412 ms
Transport
streamable HTTP
Last checked
12 November 2026

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

Description as the publisher wrote it.

The 9 tools Mlola UI offers

ToolWhat it does
check_markupChecks HTML or JSX: classes and --ml-* tokens that do not exist (with the closest that do), variant classes, data-* values and React props a component does not take, a control's class on an element that cannot be operated (ml-button on a di
Inputs: markup
check_renderChecks A2UI messages (createSurface, updateComponents, updateDataModel, deleteSurface) against the Mlola Render catalog before they render: components and props that do not exist, values a component does not offer, colors or styles set by h
Inputs: messages
get_componentEverything needed to use one item: import, every prop with fixed values (variant, tone, size, side…) and its default, the classes it styles and the data-* values each reacts to, dependencies and the install command. Set include_source to re
Inputs: name, include_source
get_design_rulesThe rules for building UI with Mlola: compose first, color by role, measure with the scales, shared state words, touch and focus; the project setup (the theme on <html>, every theme's fonts); and what each layout primitive does. Read once b
get_install_commandHow to set Mlola up: the commands to run in a project to add components, blocks, pages or templates (with the license step for Mlola Pro items), and the stylesheet link and script for a page with no build step. Leave names out for the setup
Inputs: names
get_render_catalogThe components an agent may compose at runtime with Mlola Render, as A2UI v0.9 messages: each component's props and allowed values, how surfaces, data binding and actions work, and complete examples. Read once before composing a surface. fo
Inputs: format
get_tokensThe --ml-* tokens grouped by purpose (planes and ink, color roles, spacing, type, density, shape, depth, motion, layers…). Filter with a group name or part of a token name.
Inputs: group
render_uiShows an interface in the conversation: a form, a status card, a table of results. Pass A2UI messages composed from the Mlola Render catalog (read get_render_catalog first); they are checked, and drawn with Mlola components where the host s
Inputs: messages
search_componentsFind components, blocks, pages and templates by what they do (for example 'date range', 'chat input', 'pricing'). Returns name, tier (free or Mlola Pro) and a one-line description.
Inputs: query, kind, tier

Add Mlola UI to your AI client

Every block below points at https://ui.mlola.com/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http mlola-ui https://ui.mlola.com/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "mlola-ui": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://ui.mlola.com/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "mlola-ui": {
      "url": "https://ui.mlola.com/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "mlola-ui": {
      "type": "http",
      "url": "https://ui.mlola.com/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "mlola-ui": {
      "url": "https://ui.mlola.com/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "mlola-ui": {
      "serverUrl": "https://ui.mlola.com/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "mlola-ui": {
      "url": "https://ui.mlola.com/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Mlola UI
version: 0.0.1
schema: v1
mcpServers:
  - name: Mlola UI
    type: streamable-http
    url: https://ui.mlola.com/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "mlola-ui": {
      "httpUrl": "https://ui.mlola.com/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "mlola-ui": {
      "type": "http",
      "url": "https://ui.mlola.com/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "mlola-ui": {
      "url": "https://ui.mlola.com/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fui.mlola.com%2Fmcp&type=streamable_http&id=mlola-ui&name=Mlola%20UI

Is Mlola UI up right now?

It answered our last check on 12 November 2026 in 412 ms. Over 4 checks since 27 September 2026 it answered 3. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Mlola UI

Questions about Mlola UI

How many tools does Mlola UI have?

9, as returned by the server's own tools/list on 17 November 2026: check_markup, check_render, get_component, get_design_rules, get_install_command, get_render_catalog, get_tokens, render_ui, and 1 more.

Is Mlola UI down?

It answered our last check on 12 November 2026 in 412 ms. Over 4 checks since 27 September 2026 it answered 3.

How do I add Mlola UI to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://ui.mlola.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Mlola UI need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: io.github.mlolahq. Endpoint host: ui.mlola.com. ARD identifier: urn:air:io.github.mlolahq:mcp:mlola-ui. First indexed 27 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.