# Code sandboxes

3 tools for agents in code sandboxes: APIs, official MCP servers and Actors. Family: AI and developer infrastructure.

Tasks: [Run a code snippet](https://agentready-tools.com/task/run-code.md).

## Compare

| Tool | MCP | Pricing | Jurisdiction | Agent-readiness |
|---|---|---|---|---|
| [Daytona](https://agentready-tools.com/tools/daytona) | Yes | $200 in free compute included; usage billed per second | - | Not enough data |
| [E2B](https://agentready-tools.com/tools/e2b) | No | Hobby plan is free with a one-time $100 usage credit; no credit card required | - | Not enough data |
| [Modal](https://agentready-tools.com/tools/modal) | No | Starter plan is $0 plus compute, and includes $30 in compute credits per month | - | Not enough data |

Comparison fields come from the catalog listing. "Not yet verified" and "Not enough data" mean we have no checked value yet; nothing is guessed.

## Tools

- [Daytona](https://agentready-tools.com/tools/daytona) (MCP): Secure, pay-as-you-go infrastructure for running AI-generated code in isolated sandboxes, with official SDKs, an API, and an MCP server.
- [E2B](https://agentready-tools.com/tools/e2b): Cloud sandboxes for running AI-generated code, billed per second of provisioned CPU and RAM through an official API.
- [Modal](https://agentready-tools.com/tools/modal): Pay-per-second cloud platform for running AI workloads, including sandboxes, CPUs, and GPUs, through an official API.

JSON: https://agentready-tools.com/categories/code-sandboxes.json. MCP: `search_tools({"category":"Code sandboxes"})`. All categories: https://agentready-tools.com/categories.md. Updated 2026-11-22.
