ModaDocs

Overview

Create designs with Claude and connect AI agents to your Moda canvases via MCP.

The Moda MCP server connects Claude and other AI agents to Moda through the Model Context Protocol. It works with Claude Desktop, claude.ai, Claude Code, Claude mobile, Cursor, VS Code, and other MCP-compatible environments.

Claude is the most common way people use Moda today, so the guides in this section use Claude examples first. But MCP is not Claude-specific: Cursor and other MCP-capable clients can use the same Moda tools, and OpenAI also supports MCP through its app and API surfaces.

How it works

The MCP server supports two main workflows. Design creation: ask Claude to create or edit designs directly — it generates canvases from prompts, applies your brand kit, and can remix existing designs. Design to code: paste a Moda share link and Claude fetches the design as semantic pseudo-HTML with CSS properties, then translates it to any frontend framework.

flowchart TD
A[You describe what you want] --> B[Claude calls Moda MCP tools]
B --> C[Moda's AI agent builds the canvas]
C --> D[You get a link to your design]
D --> E[Edit in Moda, export, or ask Claude to revise]

The diagram above shows the design-creation flow. The MCP server also supports the reverse — turning existing Moda designs into code.

What the agent sees

The get_moda_design tool returns output like this:

## Page: Login Screen (1440x900) [page 1]

<section
  background="#f3f4f6"
  height="900px"
  width="1440px"
  display="flex"
  justify-content="center"
  align-items="center"
>
  <Card background="#ffffff" border-radius="16px" width="600px" display="flex" flex-direction="column" gap="20px">
    <Heading font-size="32px" font-weight="700" color="#111827">Welcome back</Heading>
    <Text font-size="14px" color="#6b7280"> Sign in to your account</Text>
    <TextInput border="1px solid #d1d5db" border-radius="8px" height="48px" width="520px" placeholder="Email" />
    <button background="#2563eb" border-radius="8px" height="48px" width="520px">Sign in</button>
  </Card>
</section>

## Design Tokens - Colors: #111827, #2563eb, #6b7280, #d1d5db, #f3f4f6, #ffffff - Font Inter: weights [400, 700] roles
[body, heading] - Corner radii: 8px, 16px

The semantic tag names (Card, Button, TextInput, Heading) tell the agent what each element is, not just what it looks like. This produces better code than raw coordinates or screenshots alone.

Transport modes

The MCP server supports two transport modes:

TransportAuthUse case
stdioNoneLocal IDE integrations (Cursor, Claude Code)
streamable-httpOAuth 2.1Hosted endpoint at mcp.moda.app

The hosted server at mcp.moda.app is the easiest way to get started. See Setup for configuration details.

Available tools

Design creation

ToolDescriptionAuth required
start_design_taskCreate or edit a design from a promptYes
get_job_statusCheck progress of a design taskYes
list_jobsList recent design jobsYes
remix_designDuplicate canvas + optional AI editsYes

Brand kits

ToolDescriptionAuth required
list_brand_kitsList brand kits for a teamYes
create_brand_kitCreate brand kit from website URLYes
update_brand_kitUpdate brand kit colors, fonts, etc.Yes

Canvas management

ToolDescriptionAuth required
list_my_canvasesBrowse your canvasesYes
search_canvasesSearch canvases by nameYes
list_organizationsList your orgs and teamsYes

Design to code

ToolDescriptionAuth required
get_moda_designFetch semantic pseudo-HTML and design tokensPublic links: No, Private: Yes
get_moda_design_tokensExtract design tokens only (colors, fonts, radii)Public links: No, Private: Yes
list_moda_pagesList pages with dimensions and node countsPublic links: No, Private: Yes
export_designExport as PNG, JPEG, PDF, or PPTXPublic links: No, Private: Yes

The tables above highlight the most-used tools. The MCP server also provides set_context and get_context for session management, and upload_file for attaching files to design tasks. See the full tools reference for all 17 tools.

Next steps

On this page