Step 2. Run the MCP server

1In server.py, call the run() method on the FastMCP instance.
For example, add the following code:
if __name__ == "__main__":
mcp.run
2If necessary, add arguments to the run() call.
• - To deploy the server remotely in a cloud environment, add the argument transport="http" to use Streamable HTTP transport.
When you deploy the server locally, you don’t need to specify a transport type. The default transport type, standard input/output (STDIO), works for local deployment. However, if you want to make your intent clear, you can add the argument transport="stdio".
• - You can set a host, port, and path to bind when using HTTP transport.
• - You can set the log level to debug, info, warning, error, or critical.
The following example shows a run() call with additional arguments:
if __name__ == "__main__":
mcp.run(
transport="http",
host="127.0.0.1",
port=4200,
path="/my-custom-path",
log_level="debug",
)
3To deploy the server locally, run the server configuration file from the command line.
You can run the file using the following Python command:
python server.py
Alternatively, if you have FastMCP installed, you can run the file with the following command:
fastmcp run server.py
4To deploy the server remotely, refer to the documentation for your cloud provider.