JavaScript Sandbox
About
Provides a secure JavaScript sandbox for executing code with configurable time and memory limits, enabling safe testing and evaluation of algorithms.
Details
- Author
- garc33
- Repository
- garc33/js-sandbox-mcp-server
- GitHub stars
- 5
- Downloads
- 259
- Categories
- Developer Tools, Productivity, Design, AI, Security, Database, Frontend, Other
Jump to
- Single execute_js tool for running JavaScript code
- Isolated environment with configurable execution time (100–30000ms)
- Configurable memory limits (1MB–100MB)
- Protection against malicious or runaway code
- Easy integration with Claude Desktop via stdio
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
JavaScript SandboxCommand (node, npx, python, etc.)nodeArguments-
Argument 1
/path/to/js-sandbox/build/index.js
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
To install JavaScript Sandbox Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @garc33/js-sandbox-mcp-server --client claude
To use with Claude Desktop, add the server configuration:
execute_js
Executes JavaScript code in an isolated environment. Parameters: code (required): JavaScript code to execute, timeout (optional): Maximum execution time in milliseconds (100-30000ms), memory (optional): Memory limit in bytes (1MB-100MB). Returns the result of code execution.
- execute_js - Executes JavaScript code in an isolated environment
- Parameters:
- code (required): JavaScript code to execute
- timeout (optional): Maximum execution time in milliseconds (100-30000ms)
- memory (optional): Memory limit in bytes (1MB-100MB)
- Returns the result of code execution
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"javascript sandbox": {
"cwd": null,
"env": {},
"args": [
"/path/to/js-sandbox/build/index.js"
],
"shell": false,
"command": "node"
}
}
}Linux
{
"cwd": null,
"env": [],
"args": [
"/path/to/js-sandbox/build/index.js"
],
"shell": false,
"command": "node"
}Macos
{
"cwd": null,
"env": [],
"args": [
"/path/to/js-sandbox/build/index.js"
],
"shell": false,
"command": "node"
}Windows
{
"cwd": null,
"env": [],
"args": [
"/path/to/js-sandbox/build/index.js"
],
"shell": false,
"command": "node"
}Provides a secure JavaScript execution environment for running code snippets.
A Model Context Protocol server that provides a secure JavaScript execution environment.
- execute_js- Executes JavaScript code in an isolated environment
- Parameters:
- code(required): JavaScript code to execute
- timeout(optional): Maximum execution time in milliseconds (100-30000ms)
- memory(optional): Memory limit in bytes (1MB-100MB)
- Isolated code execution in a controlled environment
- Configurable execution time and memory limits
- Protection against malicious code
To install JavaScript Sandbox Server for Claude Desktop automatically viaSmithery:
npx -y @smithery/cli install @garc33/js-sandbox-mcp-server --client claude
To use with Claude Desktop, add the server configuration:
MacOS:~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:%APPDATA%/Claude/claude_desktop_config.json
{ "mcpServers": { "js-sandbox": { "command": "/path/to/js-sandbox/build/index.js" } } }
Since MCP servers communicate over stdio, debugging can be challenging. We recommend usingMCP Inspector, which is available as:
The Inspector will provide a URL to access debugging tools in your browser.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Help agents automatically write and test stories for your UI components
Six read-only decision tools for coding agents to assess GitHub bounties, audit agent instructions, diagnose GitHub Actions failures and flakes, and detect MCP tool drift. Remote Streamable HTTP
AI-Safe Code Analysis with 113+ MCP tools for guard validation, memory, workflow, and testing.
fable-discipline is a Claude Code plugin that makes agentic software work follow repeatable working patterns: design before code, verify after edits, separate author from reviewer, preserve verified state between sessions, and report uncertainty honestly.
MCP server that generates production-grade engineering standards (SOLID, testing, architecture, CI/CD) for AI coding assistants
Execute JavaScript code in a modern runtime environment with support for various built-in modules.
A server for JavaScript/TypeScript development with intelligent project tooling and testing capabilities.
Execute code securely in isolated sandbox environments using the E2B API.
A powerful Model Context Protocol (MCP) server that supercharges your Python development workflow with AI-powered code review, intelligent test generation, and comprehensive test execution.
Prompt optimization loops and regression test suites for Claude Code, with a companion web UI.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
