Skip to main content

UI MCP Server

CI Coverage PyPI

This project initiates at the Power of Europe Hackathon 2025.

Demo

Demo Video

https://youtu.be/o_kE_zjVRKc

Overview

ui-mcp-server is an MCP server that generates specifications for a range of UI components, containing only essential data to remain framework-agnostic. Unlike existing solutions, ui-mcp-server is data-focused, acquiring and filling data during conversation sessions while leaving rendering entirely to frontend developers (for now).

Features

  • Framework-agnostic UI component specifications
  • Data-focused approach with conversation session support
  • Full developer freedom for rendering and customization
  • Compatible with MCP clients like Cursor, Kilo and Claude Desktop

Installation

Claude Desktop

  1. Add the server to your Claude Desktop configuration file (claude_desktop_config.json):

    {
      "mcpServers": {
        "UI MCP Server": {
          "command": "full/path/to/uvx",
          "args": ["ui-mcp-server"]
        },
        // Your existing MCP servers...
      }
    }
    
  2. Restart Claude Desktop to load the MCP server.

Kilo

A working configuration looks like below:

{
  "mcpServers": {
    "ui-mcp-server":{
      "command": "full/path/to/ui-mcp-server",
      "args": []
    }
  }
}

We might have missed something as the expected version below didn't work:

{
  "mcpServers": {
    "ui-mcp-server":{
      "command": "full/path/to/uvx",
      "args": ["ui-mcp-server"]
    }
  }
}

Core concepts

  • UI-as-a-tool: ui-mcp-server provides tools that can be used to generate UI components. To this end, frequently used UI components are defined as tools, and the data required for each tool is acquired during the conversation session. The data extraction part is taken care of by AI agents using this MCP server. See our Streamlit demo for an example.
  • Component standardisation: To be agnostic of frontend frameworks, ui-mcp-server defines a standardised component library, which is basically a set of JSON schemas for UI components, with some values are predefined, and others are left to be filled by AI.

Related Projects

  • Magic MCP: Generates React components, focusing on development productivity
  • MCP UI: Similar concept to this project but with tighter coupling to specific UI implementations. Can't be used as a standalone MCP server.
  • shadcn-ui-mcp-server: Similart to MCP UI, a battery-included solution providing shadcn components as source code.

Key Differentiators

Separation of Concerns: ui-mcp-server handles UI types and conversation data exclusively, providing maximum flexibility for developers to customize and render components according to their specific needs and frameworks.

Future work

  • Define standardized component libraries for mainstream frameworks (React, Vue, Svelte, etc.)
  • Create templates to streamline frontend development workflow

Metadata

Release files for ui-mcp-server 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ui-mcp-server 0.1.0
File Size Uploaded
ui_mcp_server-0.1.0.tar.gz 73.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for ui-mcp-server 0.1.0
File Interpreter ABI Platform
ui_mcp_server-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 79.2 kB

Release files / ui_mcp_server-0.1.0.tar.gz

Download URL ui_mcp_server-0.1.0.tar.gz
Size 73.0 kB
Tags Source
SHA-256 checksum
How to use checksums
cc85dd7623bb40037c50bbbd396695fd9a0f2279e7b901d6156dd52e52f4c456
BLAKE2b-256 checksum
How to use checksums
50597d1d2755611f1c43c4ef7db569a7a8d2c24439d927299c35f86cfb0a155c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jul 27, 2025.

Transparency log

Release files / ui_mcp_server-0.1.0-py3-none-any.whl

Download URL ui_mcp_server-0.1.0-py3-none-any.whl
Size 6.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
40be233cb8923b6495d5532f8a0575ead6ce5cfdac223eeeeb0bc3b09b3d1faa
BLAKE2b-256 checksum
How to use checksums
fb303e1c2b897bb9a5542bc81cbbd8925785b2574a3494f843b137b46478e22d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jul 27, 2025.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

0.0.3

2 release files

0.0.2

2 release files

0.0.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page