genai_sandbox
No description available
Ask AI about genai_sandbox
Powered by Claude Β· Grounded in docs
I know everything about genai_sandbox. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
execution in a secure and scalable lab setup.
βοΈ Lab Virtual MCP Server (Execute Code Remotely via Claude AI) Create a virtual lab for users to run custom code remotely using the Model Context Protocol (MCP) and integrate with Claude AI or other clients.
π GitHub Repo
π¦ https://github.com/Nuvepro-Technologies-Pvt-Ltd/McpSever_Remote_code_execution.git
π This repo has moved to base/base-mcp
π What This Lab Server Does π§ Enables remote Python code execution through cline AI
π§ͺ Supports real-time lab scenarios (code evaluation, sandbox testing, etc.)
π Prerequisites Ensure you have the following on your system:
β Python 3.10.11
β pip (Python package manager)
β fastmcp (to serve the MCP endpoint)
β uv (virtual environment manager, via scoop or curl)
β Access to Claude Desktop or Cursor or cline (for testing)
π§± Installation Steps
- Clone the MCP Server Repo
git clone https://github.com/Nuvepro-Technologies-Pvt-Ltd/McpSever_Remote_code_execution.git
- Set up Python Environment
Set-ExecutionPolicy RemoteSigned -Scope CurrentUser
scoop install python
scoop install uv
cd McpSever_Remote_code_execution
- Set Up Virtual Environment
python -m venv .venv
.\.venv\Scripts\activate # Windows
source .venv/bin/activate # macOS/Linux
- Install Dependencies
pip install fastmcp
pip install cryptography
pip install shelve
- Run the Server
fastmcp run app.py
You now have a remote code execution server listening for requests via MCP.
π§ͺ MCP Client Configuration For Claude Desktop / Cursor, update your mcp_config.json:
{
"mcpServers": {
"CloudlabMcp": {
"disabled": false,
"timeout": 500,
"type": "stdio",
"command": "uv",
"args": [
"run",
"--with",
"fastmcp",
"python",
"%PROJECT_PATH%\\app.py"
],
"env": {
"API_KEY": "your_private_key",
"Baseurl": "your seed phrase here",
"compnaykey": "your_private_key"
},
"autoApprove": [*]
}
}
}
Beofre start Mcp set path
set PROJECT_PATH=D:\YourProject
cline run CloudlabMcp
β Available Tools (Prebuilt in MCP)
Tool Description execute_code Executes user-provided Python code
π‘ Recommendations for Lab Admins β Add sandboxing logic to app.py if users can run arbitrary code.
β Use Docker or subprocess isolation for safer execution (optional).
β Monitor logs and set execution timeouts.
