directRunCode
Execute code in a temporary sandbox, automatically destroying it post-execution. Supports multiple languages, custom environment variables, and optional file download. Ideal for isolated, one-time code runs without persistent sandbox operations.
Instructions
Automatically creates a sandbox, executes code, and immediately destroys the sandbox after execution. Optionally exports sandbox files (compresses multiple files into a zip archive if there are multiple files in the specified path, or exports a single file directly). Recommended for use cases that don't require continuous sandbox operations.
Input Schema
Name | Required | Description | Default |
---|---|---|---|
code | Yes | The source code to be executed in the sandbox | |
envs | No | Environment variables to be set during code execution. Supports passing custom environment variables as key-value pairs | |
is_download | No | Flag to indicate whether to download generated files. Must be enabled if the code generates files that need to be retrieved | |
language | Yes | The programming language to execute the code. If not provided or if the value is not in the allowed options, it will be treated as Python code | |
timeout | No | Maximum execution time in seconds for the sandbox. If code execution exceeds this time, it will be terminated and return a timeout error. Default is 5 |
Input Schema (JSON Schema)
You must be authenticated.
Other Tools from 302AI Sandbox MCP Server
Related Tools
- @302ai/302_sandbox_mcp
- @formulahendry/mcp-server-code-runner
- @302ai/302_sandbox_mcp
- @e2b-dev/mcp-server
- @hdresearch/mcp-python