variables.md

Demonstration of Variables in Python

Step 1: Execute Python Code

An AI agent wants to use a tool on the python-repl MCP server:

Tool: execute_python
Description: Execute Python code and return the output. Variables persist between executions.

Arguments:

{
  "code": "my_variable = \"Hello, world!\""
}

Response:

{
  "output": [
    ">>> my_variable = \"Hello, world!\""
  ]
}

The variable my_variable has been created.

Step 2: List Variables

An AI agent wants to use a tool on the python-repl MCP server:

Tool: list_variables
Description: List all variables in the current session.

Response:

{
  "Current session variables": [
    "names",
    "input",
    "exit",
    "my_variable"
  ]
}

The variables in the current session are names, input, exit, and my_variable. The names() function is the one that is used internally to generate the list of names. my_variable is the one the AI agent created.

Step 3: Execute Python Code

An AI agent wants to use a tool on the python-repl MCP server:

Tool: execute_python
Description: Execute Python code and return the output. Variables persist between executions.

Arguments:

{
  "code": "print(my_variable)"
}

Response:

{
  "output": [
    ">>> print(my_variable)",
    "Hello, world!"
  ]
}

The variable my_variable still has its value the AI agent set earlier.