Crypto Projects MCP Server
About
An MCP server that provides cryptocurrency project data to AI agents
Details
- License
- MIT license
Explore
- Fetch Project Data: Retrieve comprehensive project details (e.g., market data, tokenomics, and links) from Mobula.
- Structured Output: Format project data into a well-organized Markdown document with sections for overview, market data, investors, exchanges, token distribution, and release schedules.
- Language Support: Customize output language based on system locale or user-specified settings.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Crypto Projects MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Python 3.10 or higher
- uv for package management and running the project
- Mobula API access (no authentication required for public endpoints)
Test the server using the MCP Inspector:
uv run mcp dev main.py
The get_project_data tool retrieves raw JSON data for a specified cryptocurrency project. This is useful for applications needing unprocessed data.
await get_project_data("avalanche")
This returns a dictionary containing details like price, market cap, blockchain, and social links for Avalanche. Example output:
{
"name": "Avalanche",
"symbol": "AVAX",
"blockchains": ["Avalanche C-Chain"],
"price": 35.12,
"market_cap": 1234567890,
...
}
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"crypto projects mcp server": {
"crypto-projects-mcp": {
"command": "uv",
"args": [
"sync"
]
}
}
}
}McpServers
{
"crypto-projects-mcp": {
"command": "uv",
"args": [
"sync"
]
}
}An MCP server that provides cryptocurrency project data from Mobula.io to AI agents.
Features
- Fetch Project Data: Retrieve comprehensive project details (e.g., market data, tokenomics, and links) from Mobula.
- Structured Output: Format project data into a well-organized Markdown document with sections for overview, market data, investors, exchanges, token distribution, and release schedules.
- Language Support: Customize output language based on system locale or user-specified settings.
Installation
Prerequisites
- Python 3.10 or higher
- uv for package management and running the project
- Mobula API access (no authentication required for public endpoints)
Setup
1. Clone the Repository:
git clone https://github.com/kukapay/crypto-projects-mcp.git
cd crypto-projects-mcp
2. Install Dependencies:
uv sync
Usage
Running in Development Mode
Test the server using the MCP Inspector:
uv run mcp dev main.py
Integrating with Claude Desktop
Install the server in Claude Desktop for LLM interaction:
uv run mcp install main.py --name "Crypto Projects"
Example Interaction
The server provides two primary interfaces: a tool to fetch raw data and a prompt to format it into a structured Markdown document.
1. Using the get_project_data Tool
The get_project_data tool retrieves raw JSON data for a specified cryptocurrency project. This is useful for applications needing unprocessed data.
await get_project_data("avalanche")
This returns a dictionary containing details like price, market cap, blockchain, and social links for Avalanche. Example output:
{
"name": "Avalanche",
"symbol": "AVAX",
"blockchains": ["Avalanche C-Chain"],
"price": 35.12,
"market_cap": 1234567890,
...
}
2. Using the format_project_data Prompt
The format_project_data prompt fetches data using the get_project_data tool and formats it into a comprehensive Markdown document. This prompt is designed for LLM applications to present structured, human-readable information about a cryptocurrency project.
```python
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
