# Code Execution Tools — AI Agents and Tool Use

Source: https://www.geekswithgeeks.com/en/ai-agents-mcp/kinds-code-exec

> Let an agent run code for exact computation, inside a sandbox.

## Let code do the arithmetic

Models can make slips in arithmetic, date maths and data wrangling. A **code-execution tool** lets the agent write a small script, run it and read the output, so numbers come from computation rather than recall. Because the code is model-written, run it in a **sandbox**: no access to your secrets, limited files, no unrestricted network, and a time limit.

## A limited runner

This sketch uses a subprocess with a timeout. A subprocess alone is NOT a real sandbox; production systems use containers or dedicated sandboxes with no secrets mounted.

```python
import subprocess, sys

def run_python(code: str, timeout_s: int = 5) -> str:
    try:
        p = subprocess.run([sys.executable, "-c", code],
                           capture_output=True, text=True, timeout=timeout_s)
    except subprocess.TimeoutExpired:
        return "Error: timed out"
    return (p.stdout + p.stderr)[:2000]      # clip the output
```

**Quiz:** Why run model-written code in a sandbox?

- [ ] Python requires it
- [ ] Sandboxes make code faster
- [ ] The code is always correct
- [x] To limit the damage of mistakes or malicious code

*Answer:* To limit the damage of mistakes or malicious code. Isolation contains whatever the generated code does, intended or not.