pixso-mcp-server
Brings Pixso design context into AI coding workflows, enabling AI assistants to understand design layers, component variants, variables, and local styles for design-to-code tasks.
README
Pixso MCP Server
Bring Pixso design context into your AI coding workflow. Pixso MCP Server helps AI assistants understand design layers, component variants, variables, and local styles so they can answer design questions and produce implementation-ready code.
What you can do
- Turn a selected Pixso layer into React, Vue, HTML/CSS, or other frontend code.
- Inspect layout, hierarchy, text, fills, typography, effects, and other layer details.
- Understand every state and property combination in a component variant set.
- Extract design variables and variable groups for design-token workflows.
- Review local color, text, effect, and grid styles from a design file.
- Compare an implementation with its design source or generate theme configuration.
Available tools
| Tool | What it provides | Required input |
|---|---|---|
get_node_dsl |
Structured details for a selected layer, including its hierarchy, layout, content, and visual properties. This is the main tool for design-to-code tasks. | file_key, guid |
get_variants |
All variants associated with a component set, a variant component, or an instance whose main component belongs to a variant set. | file_key, guid |
get_variable_sets |
The variable groups defined in a design file, useful for understanding its token organization. | file_key |
get_variables |
Design variables associated with the selected layer, such as reusable colors, spacing, sizes, and other token values. | file_key, guid |
get_local_styles |
Reusable local styles defined in the file, including color, text, effect, and grid styles. | file_key |
You normally do not need to choose a tool yourself. Share a Pixso link and tell your AI assistant what you want; it can select the appropriate tool.
Requirements
- Node.js 20 or newer
- A Pixso account and valid Pixso Token
- An MCP-compatible AI coding client
Configure your MCP client
Add the following server entry to your MCP client configuration:
{
"mcpServers": {
"pixso": {
"command": "npx",
"args": [
"-y",
"@pixso/pixso-stdio-mcp",
"--token",
"YOUR_PIXSO_TOKEN"
]
}
}
}
Replace YOUR_PIXSO_TOKEN with your Pixso Token, then restart or reconnect the
server in your MCP client. The default Pixso URL is https://pixso.cn/api/mcp/mcp.
Private or custom Pixso deployment
If your organization uses another Pixso deployment, add its complete MCP URL:
{
"mcpServers": {
"pixso": {
"command": "npx",
"args": [
"-y",
"@pixso/pixso-stdio-mcp",
"--url",
"https://example.pixso.cn/api/mcp/mcp",
"--token",
"YOUR_PIXSO_TOKEN"
]
}
}
}
Keep your Token private. Do not commit a real Token to a repository or include it in screenshots, logs, or issue reports.
Use a Pixso design link
Copy a link to the layer you want the AI assistant to inspect. A layer link looks like this:
https://{pixso-domain}/app/design/{file_key}?item-id={guid}
file_keyidentifies the design file.item-idis the layerguidused by layer-specific tools.page-idis not a layerguid. For layer-specific tasks, share a link that containsitem-id.
File-level tools such as get_variable_sets and get_local_styles only need the
design file and can work without a selected layer.
Example requests
Implement this Pixso layer as a React component using Tailwind CSS:
https://pixso.cn/app/design/FILE_KEY?item-id=LAYER_GUID
Analyze all variants of this button component and generate its TypeScript props.
Extract the variables and local styles from this design file and generate CSS
custom properties for the project theme.
Explain the layout, typography, colors, and spacing used by this selected layer.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.