Tokens MCP
by antonkulaga
Tokens MCP is an MCP server for the Token Metrics API, providing a standardized interface for AI systems to access cryptocurrency market data. It simplifies working with crypto data and strategy development for algorithmic trading bots or market research.
Last updated: N/A
What is Tokens MCP?
Tokens MCP is an MCP (Model Control Protocol) server that provides a standardized interface for AI systems to access the TokenMetrics API. It allows users to access comprehensive cryptocurrency market data and implement trading strategies.
How to use Tokens MCP?
To use Tokens MCP, clone the repository, install dependencies using uv sync, configure your TokenMetrics API key in .env and mcp_server_config.json, and then run the server using uv run mcp run run.py. The server can then be integrated with IDEs like Cursor that support MCP.
Key features of Tokens MCP
Access comprehensive cryptocurrency market data
Implement and backtest trading strategies
Generate visual performance metrics
Analyze token performance across different timeframes
Use cases of Tokens MCP
Algorithmic trading bots
Market research
Automated trading systems
AI-powered crypto analysis
FAQ from Tokens MCP
What is MCP?
What is MCP?
MCP (Model Control Protocol) provides a standardized interface for AI systems to access external tools and data sources.
What API does this server use?
What API does this server use?
This server uses the TokenMetrics API to access cryptocurrency market data.
How do I configure the API key?
How do I configure the API key?
Copy .env.example to .env and configure your API keys. You must also update the mcp_server_config.json file with your TokenMetrics API key.
What IDEs are supported?
What IDEs are supported?
Cursor provides native support for MCP, allowing AI assistants to directly interact with the TokenMetrics API through this server.
Are there any known issues?
Are there any known issues?
Yes, the mcp_server_config.json file currently contains absolute paths to the server that need to be manually updated. Also, the test files are manually run scripts rather than proper pytest files. Many TokenMetrics API endpoints had to be implemented directly because they are not available in the existing tmai-api library.