Code Runner

​

Key Features

• Python 3.11+ - Full Python stdlib
• JavaScript/Node.js - Modern ES6+ support
• Sandboxed - Isolated from system and other sessions
• 30-second timeout - Prevents runaway code
• No Network Access - Isolated from external services
• Input/Output Handling - Pass data to code and capture results
• No Dependencies - Core libraries only (upgrade to Sandbox for pip/npm)

​

How to Enable

​

For Agents

1. Agents > Select Agent > Settings > Capabilities
2. Attach Code Runner

​

For MCP Gateways

1. Gateways > Select Gateway > Capabilities
2. Attach Code Runner

​

Usage Examples

​

Python Calculation

# Calculate factorial
def factorial(n):
    return 1 if n <= 1 else n * factorial(n - 1)

result = factorial(5)
print(f"5! = {result}")

5! = 120

​

JavaScript Data Processing

const data = [1, 2, 3, 4, 5];
const sum = data.reduce((a, b) => a + b, 0);
const average = sum / data.length;
console.log(`Average: ${average}`);

Average: 3

​

JSON Parsing

import json

data = '{"name": "Alice", "age": 30}'
parsed = json.loads(data)
print(parsed['name'])

Alice

​

Input/Output

​

Pass Data to Code

# Receive input from agent
input_data = {"numbers": [1, 2, 3, 4, 5]}
total = sum(input_data["numbers"])
print(total)

​

Return Structured Data

result = {
    "status": "success",
    "total": 15,
    "average": 3.0
}
print(result)

​

Available Libraries

​

Python Standard Library

• json, csv, re, datetime, math, statistics
• collections, itertools, functools
• hashlib, urllib, base64
• logging, pprint, sys, os (limited)

​

JavaScript Standard Library

• All ES6+ features
• JSON, Math, Date, RegExp
• Array methods, String methods
• No external npm packages

​

Resource Limits

​

Limitations

• No network access
• No file I/O (use Files capability instead)
• No package installation (use Sandbox for pip/npm)
• No background processes
• No system calls

​

Cost

​

Common Recipes

​

Format Data

data = "hello,world,test"
items = data.split(",")
formatted = [item.upper() for item in items]
print(",".join(formatted))

​

Calculate Statistics

import statistics
values = [10, 20, 30, 40, 50]
print(f"Mean: {statistics.mean(values)}")
print(f"Median: {statistics.median(values)}")

​

Transform JSON

import json
input_json = '{"a": 1, "b": 2}'
data = json.loads(input_json)
output = {k: v * 2 for k, v in data.items()}
print(json.dumps(output))

​

Troubleshooting

​

Timeout Error

​

Memory Error

​

Module Not Found

​

No Output Captured

​

When to Use

​

Next Steps

• Sandbox - Full Compute
• Files - Persistent Storage
• HTTP Client - API Access