Tokens MCP
About
Tokens MCP is a Model Context Protocol server that provides a standardized interface for AI systems to access the Token Metrics API. It enables access to comprehensive cryptocurrency market data, backtesting trading strategies, generating visual performance metrics, analyzing…
Details
- License
- Apache-2.0 license
Explore
- Access comprehensive cryptocurrency market data
- Implement and backtest trading strategies (e.g., moving average crossovers)
- Generate visual performance metrics for strategies
- Analyze token performance across different timeframes
- Build automated trading systems with consistent API access
- Integrates with IDEs supporting the Model Context Protocol
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
Tokens MCPCommand (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
1. Clone the repository:
git clone https://github.com/antonkulaga/tokens-mcp.git
2. Install dependencies:
uv sync
uv run mcp run run.py
You can inspect the server by running
uv run mcp dev run.py
Note: if uv environment is activated you can omit uv run part
The mcp_server_config.json file currently contains absolute paths to the server. You must manually edit this file to update the path to match your local environment:
{
"mcpServers": {
"TmaiAPI": {
"command": "uv",
"args": ["--directory", "/path/to/tokens-mcp", "run", "mcp", "run", "run.py"],
^^^^^^^^^^^^^^^^^^^
Update this to your actual path
"env": {
"TOKEN_METRICS_API_KEY": "your-api-key-here"
}
}
}
}
This is a temporary limitation that will be addressed in future updates.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"tokens mcp": {
"tokens-mcp": {
"command": "uv",
"args": [
"sync"
]
}
}
}
}McpServers
{
"tokens-mcp": {
"command": "uv",
"args": [
"sync"
]
}
}MCP server for Token Metrics API.
About
MCP (Model Control Protocol) provides a standardized interface for AI systems to access external tools and data sources. This repository implements an MCP server for TokenMetrics API, enabling you to:
- Access comprehensive cryptocurrency market data
- Implement and backtest trading strategies (like moving average crossovers)
- Generate visual performance metrics for your strategies
- Analyze token performance across different timeframes
- Build automated trading systems with consistent API access
Whether for algorithmic trading bots or market research, this server simplifies working with crypto data and strategy development.
Demo Video
Getting Started
Installation
1. Clone the repository:
git clone https://github.com/antonkulaga/tokens-mcp.git
2. Install dependencies:
uv sync
Configuration
Copy .env.example to .env and configure your API keys:
```bash
cp .env.example .env
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
