Codesandbox MCP
C

Codesandbox MCP

The CodeSandbox MCP server exposes CodeSandbox SDK operations through tools for AI agents to perform operations such as sandbox creation and file read and write.
2.5 points
7.7K

What is the CodeSandbox MCP Server?

The CodeSandbox MCP Server is a bridge connecting AI assistants with cloud development environments. It allows AI tools like Claude and Cursor to directly create, manage, and operate development sandboxes in CodeSandbox, enabling operations such as code editing, file management, and environment configuration without human intervention.

How to use the CodeSandbox MCP Server?

By configuring an MCP client (such as Claude Desktop or Cursor), set this server as the tool provider. After the AI assistant is authorized, it can call various tools to operate the CodeSandbox sandbox, including creating new projects, reading and writing files, and managing virtual machines.

Applicable Scenarios

Suitable for scenarios such as AI-assisted programming, automated code generation, cloud development environment management, team collaboration code review, and educational programming demonstrations. Particularly suitable for projects requiring rapid prototype development and remote collaboration.

Main Features

Full Lifecycle Management of Sandboxes
Create, start, hibernate, update, and obtain sandbox information. Support rapid project creation from templates.
File System Operations
Read and write files, list directory contents, rename and move files. Support UTF-8 and Base64 encoding.
Session Management
Create and resume development sessions. Support read and write permission control and environment variable configuration.
Virtual Machine Control
Control the resource level (from Pico to XLarge), hibernation timeout, and automatic wake-up configuration of the sandbox virtual machine.
Stateless Design
Each call is executed independently without retaining server-side state, ensuring the security and repeatability of operations.
Read-Only Mode Support
Can be configured as read-only mode to prevent accidental modification, suitable for security-sensitive environments.
Advantages
Seamlessly integrate AI assistants with cloud development environments
Support complete file operations and project management
Flexible virtual machine resource configuration
Stateless design ensures operation security
Support rapid project creation from templates
Configurable permission control (read-write/read-only)
Limitations
Requires CodeSandbox API token authorization
Only supports the new version of CodeSandbox sandboxes (VM), not the old version of projects
File operations require establishing a connection each time
Network latency may affect operation response speed
Requires a Node.js 18+ runtime environment

How to Use

Get an API Token
Create a personal access token in the CodeSandbox account settings. It needs to include permissions for sandbox creation, read and write editing, virtual machine management, and preview token management.
Configure the MCP Client
In MCP-supported clients such as Claude Desktop or Cursor, add this server to the mcp.json configuration file.
Start the Server
The client will automatically start the server, or you can manually start it through the command line for testing.
Use via an AI Assistant
In the supported AI assistant interface, you can now use CodeSandbox-related tools to manage the development environment.

Usage Examples

Quickly Create a React Application Prototype
The AI assistant quickly creates a React application sandbox according to user requirements and adds necessary components and configurations.
Batch Modify Project Files
The AI assistant batch updates configuration files or code files in an existing project.
Environment Configuration Management
Configure different virtual machine resources and environment variables for sandboxes with different purposes.
Team Code Review Assistance
The AI assistant accesses team members' sandboxes for code review and suggestions.

Frequently Asked Questions

What kind of CodeSandbox account permissions are required?
Will this server save my code or data?
Which MCP clients are supported?
What does virtual machine hibernation mean?
How to ensure operation security?
Is there a delay in operations?
Does it support team collaboration?
How to debug problems?

Related Resources

CodeSandbox Official Documentation
Complete documentation and API reference for the CodeSandbox platform.
Model Context Protocol Specification
Official specification and implementation guide for the MCP protocol.
GitHub Repository
Project source code and issue tracking.
npm Package Page
Latest version and installation statistics.
Claude Desktop Configuration Guide
How to configure Claude Desktop to use the MCP server.
CodeSandbox API Reference
Complete CodeSandbox REST API documentation.

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "codesandbox": {
      "command": "npx",
      "args": [
        "-y",
        "@techlibs/codesandbox-mcp@latest",
        "--read-only"
      ],
      "env": {
        "CODESANDBOX_API_TOKEN": "<your-api-token>"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
6.5K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
6.4K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
4.6K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.7K
4 points
P
Paperbanana
Python
7.0K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
7.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.8K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
6.7K
5 points
N
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
21.8K
4.5 points
G
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
26.1K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.8K
4.3 points
M
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
35.2K
5 points
U
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#
33.1K
5 points
F
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
65.9K
4.5 points
G
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
21.3K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
98.0K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase