Quickjs Sandbox
A secure JavaScript execution service based on the MCP protocol
rating : 2.5 points
downloads : 26
What is the MCP Quick JS Runner?
The MCP Quick JS Runner is a secure tool that allows you to run JavaScript code in an isolated environment. It ensures the security and stability of code execution through the QuickJS engine and Node.js WASI technology.How to use the MCP Quick JS Runner?
Simply start the server and send a request containing JavaScript code to get the execution result.Applicable scenarios
Suitable for scenarios that require secure code execution, such as model training, test scripts, or small projects.Main features
Secure execution environmentRun code in the QuickJS engine to ensure that the system is not affected by potentially malicious code.
Standard input/output captureAutomatically capture console output (stdout/stderr) during code execution.
Error reportingCapture and return any runtime errors or non - zero exit codes.
MCP integrationProvide services as a standard MCP tool for easy integration with other tools.
Advantages and limitations
Advantages
Strong security to prevent code from threatening the host system
Support the execution of various JavaScript codes
Easy to integrate into existing systems
Limitations
Dependent on Node.js and QuickJS environments
May require high - end hardware resources to support large - scale concurrent execution
How to use
Install dependencies
Ensure that Node.js (recommended version 23.x and above) and npm/yarn are installed.
Start the server
Run the server.ts file to start the MCP server.
Send a request
Send a request containing JavaScript code to the server via the MCP protocol.
Usage examples
Example 1: Simple printingExecute a simple JavaScript code to output 'Hello World'.
Example 2: Calculate an expressionExecute a mathematical operation and return the calculation result.
Frequently Asked Questions
How to ensure the security of code execution?
Does it support all types of JavaScript code?
How to clean up temporary files?
Related resources
MCP official documentation
Understand the basic knowledge of the MCP protocol.
QuickJS GitHub repository
Get the source code of the QuickJS engine.
Node.js official website
Download and install Node.js.
Featured MCP Services

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
867
4.3 points

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
178
4.5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
129
4.3 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.8K
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
595
5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
784
4.8 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
317
4.5 points