Pricing

Pay per usage

Try for free

Go to Apify Store

AI Code Sandbox

Try for free

Provides a secure execution environment for code generated by AI agents. Interact with the sandbox through web shell, REST API, or MCP. Supports Python and Node.js runtimes, Claude Code, Codex CLI, and OpenCode coding agents, and persists state.

Pricing

Pay per usage

Rating

5.0

(3)

Developer

Apify

Actor stats

Bookmarked

Total users

Monthly active users

16 hours ago

Last modified

Categories

Agents

Developer tools

Open source

You can access the AI Code Sandbox programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

1from apify_client import ApifyClient
2
3# Initialize the ApifyClient with your Apify API token
4# Replace '<YOUR_API_TOKEN>' with your token.
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7# Prepare the Actor input
8run_input = {
9    "agentSkills": """apify/agent-skills
10# One skill per line — owner/repo or a GitHub repo URL:
11# anthropics/skills
12# https://github.com/anthropics/skills""",
13    "nodeDependencies": """# One package@version per line (omit @version for latest):
14# zod@^3.0
15# axios""",
16    "pythonRequirements": """# One package per line:
17# requests==2.31.0
18# pandas""",
19    "initBashScript": """#!/bin/bash
20# Runs on startup. Uncomment or add your own:
21# apt-get update && apt-get install -y jq
22# mkdir -p /sandbox/data""",
23    "idleTimeoutSecs": 900,
24    "bridges": [{
25            "path": "/myapp",
26            "target": "http://127.0.0.1:3000/myapp",
27        }],
28}
29
30# Run the Actor and wait for it to finish
31run = client.actor("apify/ai-code-sandbox").call(run_input=run_input)
32
33# Fetch and print Actor results from the run's dataset (if there are any)
34print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
35for item in client.dataset(run["defaultDatasetId"]).iterate_items():
36    print(item)
37
38# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

AI Code Sandbox API in Python

The Apify API client for Python is the official library that allows you to use AI Code Sandbox API in Python, providing convenience functions and automatic retries on errors.

Install the apify-client

$pip install apify-client

Other API clients include:

AI Code Sandbox API in JavaScript

AI Code Sandbox API through CLI

AI Code Sandbox OpenAPI definition

AI Code Sandbox API

TEST Dach - SANDBOX

xmiso_scrapers/test-dach-sandbox

Do not use

Miso

SANDBOX Spfy Test Actor

xmiso_scrapers/sandbox-shopify-shops-test-actor

do not use this, for testing purposes only

Miso

SANDBOX 10M+ GMAPS

xmiso_scrapers/sandbox-10m-gmaps

DO NOT USE. Test Actor for prepared features

Miso

AI Repository Security Scanner

optimus-fulcria/ai-repo-security-scanner

Scan AI/ML repositories for vulnerabilities: sandbox escapes, code injection, path traversal. For security teams.

Fulcria Labs

Mcp Gateway

maximus242/mcp-gateway

Convert any REST API into an MCP server for AI agents

Philip

Tavily Search MCP Server - Fast AI Web Search for Agents

clearpath/tavily-search-mcp

Search the web through AI assistants via MCP. Tavily's AI search engine with ranked results, AI answers, images, and full page content. No API key needed. Works with Claude, ChatGPT, any MCP client.

ClearPath

Ui Generator

tinkerbrains/ui-generator

Get UI designs for your app ideas. Get HTML + TailwindCSS code and a full screenshot of the design in output data. You will need a Anthropic Claude API Key to add in environment variables.

Sanket Dongre

5.0

Web Search MCP Server

abotapi/ai-search-mcp-server

An Apify MCP Server that provides real-time web search capabilities for AI agents via the Model Context Protocol (MCP).

AbotAPI

Openapi To Mcp Converter

theguide/openapi-to-mcp-converter

Convert any OpenAPI specification into a Model Context Protocol (MCP) server that AI assistants can use to interact with REST APIs.

TheGuide

MCP Web Scraper Server — AI-Ready Web Scraping via MCP

junipr/mcp-web-scraper

Model Context Protocol (MCP) server for web scraping. Provides scrape, extract, search, and link discovery tools via SSE or WebSocket transport. Connect AI agents and LLMs to live web data.