Sponsored by Deepsite.site

Uranium Mcp

Created By
xkelxmc3 months ago
MCP for Uranium NFT tools to mint, list, and manage digital assets on the permaweb.
Content

Uranium MCP Server

🚀 Quick Install

Install in VS Code Install in VS Code Insiders Install in Cursor Install in Goose Install in LM Studio

A Model Context Protocol (MCP) server for working with portal.uranium.pro - creating and managing NFT collections and assets. This server enables LLMs to interact with blockchain NFTs through a simple, structured interface.

Key Features

  • Fast and efficient NFT management. Direct integration with Uranium API for instant operations.
  • Multi-collection support. Manage ERC721 and ERC1155 NFT collections seamlessly.
  • File-based asset creation. Upload images, videos, audio, and documents directly as NFTs.
  • Bulk operations. List and filter assets across multiple collections with pagination.

Requirements

  • Node.js 18 or newer
  • Uranium API key from portal.uranium.pro
  • VS Code, Cursor, Windsurf, Claude Desktop, Goose or any other MCP client

Getting Started

First, install the Uranium MCP server with your client.

Standard config works in most of the tools:

{
  "mcpServers": {
    "uranium": {
      "command": "npx",
      "args": ["uranium-tools-mcp@latest"],
      "env": {
        "URANIUM_API_KEY": "your_api_key_here"
      }
    }
  }
}
Claude Code

Use the Claude Code CLI to add the Uranium MCP server:

claude mcp add uranium npx uranium-tools-mcp@latest

Then set your URANIUM_API_KEY when prompted.

Claude Desktop

Add to your Claude Desktop configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "uranium": {
      "command": "npx",
      "args": ["uranium-tools-mcp@latest"],
      "env": {
        "URANIUM_API_KEY": "your_api_key_here"
      }
    }
  }
}
Codex

Create or edit the configuration file ~/.codex/config.toml and add:

[mcp_servers.uranium]
command = "npx"
args = ["uranium-tools-mcp@latest"]
env = { URANIUM_API_KEY = "your_api_key_here" }

For more information, see the Codex MCP documentation.

Cursor

Click the button to install:

Install in Cursor

Or install manually:

Go to Cursor Settings -> MCP -> Add new MCP Server. Name it "uranium", use command type with the command npx uranium-tools-mcp@latest. Add environment variable URANIUM_API_KEY with your API key.

Gemini CLI

Follow the MCP install guide, use the standard config above with your API key.

Goose

Click the button to install:

Install in Goose

Or install manually:

Go to Advanced settings -> Extensions -> Add custom extension. Name it "uranium", use type STDIO, and set the command to npx uranium-tools-mcp@latest. Add environment variable URANIUM_API_KEY with your API key. Click "Add Extension".

LM Studio

Click the button to install:

Add MCP Server uranium to LM Studio

Or install manually:

Go to Program in the right sidebar -> Install -> Edit mcp.json. Use the standard config above with your API key.

opencode

Follow the MCP Servers documentation. For example in ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "uranium": {
      "type": "local",
      "command": [
        "npx",
        "uranium-tools-mcp@latest"
      ],
      "env": {
        "URANIUM_API_KEY": "your_api_key_here"
      },
      "enabled": true
    }
  }
}
Qodo Gen

Open Qodo Gen chat panel in VSCode or IntelliJ → Connect more tools → + Add new MCP → Paste the standard config above with your API key.

Click Save.

VS Code

Click the button to install:

Install in VS Code Install in VS Code Insiders

Or install manually:

Follow the MCP install guide, use the standard config above. You can also install the Uranium MCP server using the VS Code CLI:

# For VS Code
code --add-mcp '{"name":"uranium","command":"npx","args":["uranium-tools-mcp@latest"],"env":{"URANIUM_API_KEY":"your_api_key_here"}}'

After installation, the Uranium MCP server will be available for use with your GitHub Copilot agent in VS Code.

Windsurf

Follow Windsurf MCP documentation. Use the standard config above with your API key.

Configuration

Environment Variables

  • URANIUM_API_KEY (required): Your Uranium API key from portal.uranium.pro
  • URANIUM_BASE_URL (optional): API base URL. Defaults to https://gw.urnm.pro

Example Configuration

{
  "mcpServers": {
    "uranium": {
      "command": "npx",
      "args": ["uranium-tools-mcp@latest"],
      "env": {
        "URANIUM_API_KEY": "your_api_key_here"
        // URANIUM_BASE_URL is optional, defaults to https://gw.urnm.pro
      }
    }
  }
}

Local Installation

If you prefer to install locally:

npm install -g uranium-tools-mcp
# or
pnpm add -g uranium-tools-mcp
# or
yarn global add uranium-tools-mcp

Then use uranium-tools-mcp instead of npx uranium-tools-mcp@latest in the configuration.

Tools

This MCP server provides 4 main tools for NFT management:

Collection Management

list_collections

  • Description: List all user collections (personal, common, and external)
  • Parameters: None

create_collection

  • Description: Create a new NFT collection
  • Parameters:
    • name (string, required): Collection name (3-30 characters, letters, numbers, and [_.-] symbols) [min length: 3, max length: 30]
    • symbol (string, required): Collection symbol (3-30 characters, letters, numbers, and underscores) [min length: 3, max length: 30]
    • type (string, enum: ERC721, ERC1155, required): Collection type: ERC721 (single NFTs) or ERC1155 (multi-token)
Asset Management

list_assets

  • Description: List assets with optional filtering by collection, search, and pagination
  • Parameters:
    • contractId (string, optional): Filter assets by collection ID
    • page (number, optional): Page number (default: 1) [min: 1, default: 1]
    • pageSize (number, optional): Number of assets per page (default: 20, max: 100) [min: 1, max: 100, default: 20]
    • sortBy (string, optional): Sort field (default: createdAt) [default: "createdAt"]
    • order (string, enum: asc, desc, optional): Sort order (default: asc) [default: "asc"]
    • quickFilter (string, optional): Search text to filter assets by title

create_asset

  • Description: Create a new NFT asset from a local file or base64 data
  • Parameters:
    • filePath (string, optional): Absolute path to the media file (for local files)
    • fileData (string, optional): Base64 encoded file data (for Claude Desktop)
    • fileName (string, optional): Original filename (required when using fileData)
    • mimeType (string, optional): MIME type of the file (required when using fileData, e.g., 'image/png')
    • contractId (string, required): ID of the collection to mint the asset in
    • title (string, required): Asset title (3-120 characters) [min length: 3, max length: 120]
    • description (string, optional): Asset description (optional, max 255 characters) [max length: 255]
    • location (string, optional): Location where the asset was created (optional, max 100 characters) [max length: 100]
    • editions (number, optional): Number of editions (for ERC1155 collections only, 1-1000) [min: 1, max: 1000]
    • shareWithCommunity (boolean, optional): Make the asset discoverable by the community (optional, default: false) [default: false]

Supported File Formats

  • Images: JPG, JPEG, PNG, GIF, WebP, SVG
  • Video: MP4, WebM, MOV, AVI
  • Audio: MP3, WAV, OGG
  • Documents: PDF, TXT

Development

Building from Source

  1. Clone the repository:
git clone https://github.com/xkelxmc/uranium-mcp.git
cd uranium-mcp
  1. Install dependencies:
npm install
  1. Build the project:
npm run build

Development Commands

# Compile in watch mode
npm run dev

# Build for production
npm run build

# Start server locally
npm start

# Clean build directory
npm run clean

Testing

Using MCP Inspector

Test your MCP server with the MCP Inspector:

# For installed version
npx @modelcontextprotocol/inspector uranium-tools-mcp

# For local development
npm run build:dev
npx @modelcontextprotocol/inspector node build/index.js

Development Testing

# Test with stdio transport
npm run dev:stdio

# Test with HTTP transport
npm run dev:http

# Inspect with HTTP transport
npm run mcp:inspect

Troubleshooting

Common Issues

  1. API Key not working: Make sure your API key is valid and has the necessary permissions at portal.uranium.pro

  2. Connection errors: Check that the URANIUM_BASE_URL is correct (defaults to https://gw.urnm.pro)

  3. File upload issues: Ensure the file path is absolute and the file exists

  4. Collection creation fails: Verify that collection names and symbols follow the required format (3-30 characters, alphanumeric and underscore)

Project Structure

src/
├── api/           # Complete copy of Uranium API from Raycast
├── utils/         # Utilities for validation, formatting, etc.
├── models/        # Upload primitives for working with files
├── tools/         # MCP tools
├── server.ts      # MCP server configuration
├── index.ts       # Entry point
└── config.ts      # API and MCP configuration

License

todo

Support

For issues and questions:

Server Config

{
  "mcpServers": {
    "uranium": {
      "command": "npx",
      "args": [
        "uranium-tools-mcp@latest"
      ],
      "env": {
        "URANIUM_API_KEY": "your_api_key_here"
      }
    }
  }
}
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
WindsurfThe new purpose-built IDE to harness magic
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Serper MCP ServerA Serper MCP Server
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Playwright McpPlaywright MCP server
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
ChatWiseThe second fastest AI chatbot™
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Tavily Mcp
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
CursorThe AI Code Editor
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
Amap Maps高德地图官方 MCP Server
DeepChatYour AI Partner on Desktop