LABSCO SUMMARY
A price feed you can extend, rather than a finished product.
The crypto tool is one file in a project that is mostly scaffolding — settings per environment, schemas, service and resource layers already separated. If what you want is prices, the setup is a key and a run command. If what you want is your own tools against your own API, the interesting part is the structure already sitting around that one tool.
What it is
A Python MCP server that answers with cryptocurrency price information, reading from CoinMarketCap. It ships with an environment-based configuration so the same code runs locally, in staging and in production.
What you get
- Real-time cryptocurrency price retrieval through the CoinMarketCap API
- Configuration switched by environment — local, development, staging and production each get their own settings
- A Docker image for running it as a container instead of a local process
- A documented pattern for adding your own tools: define the function, register it, document it with a docstring
Requirements
The project python-server-mcp, version 0.1.0, run from a checkout with uv: uv venv, activate it, uv sync, then python main.py for stdio. Python 3.12 or higher. Two settings go in a .env file or the client's env block: COINMARKETCAP_API_KEY and ENVIRONMENT. The Docker path builds mcp/python-server-mcp and passes both variables through.
Setup effort
Run a container — build the image from the repository, then point your client at it
USE CASES
01
Asking what a coin is trading at right now
Get a live price from CoinMarketCap rather than whatever the model last saw in training.
02
Running the same server in more than one environment
Switch environments with one variable and let the settings module pick the right configuration.
03
Adding your own tool to a working server
Follow the documented three steps — define, register, document — instead of starting a project from nothing.
BEFORE YOU INSTALL
What to know first
Requires
- docker on PATH
- Python 3.12+
- COINMARKETCAP_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Build the image from the repository, then point your client at it.
Server setup
TERMINAL
git clone https://github.com/stevearagonsite/PythonServerMcp
cd PythonServerMcp
docker build -t mcp/python-server-mcp -f Dockerfile .MCP Clients
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"python-server-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-p",
"8000:8000",
"-e",
"ENVIRONMENT",
"-e",
"COINMARKETCAP_API_KEY",
"mcp/python-server-mcp"
],
"env": {
"ENVIRONMENT": "PRODUCTION",
"COINMARKETCAP_API_KEY": "<YOUR_COINMARKETCAP_API_KEY>"
}
}
}
}