About Dynamic Shell Server
Dynamic Shell Server is an MCP server that runs shell commands under a dynamic approval system. It is aimed at developers who want an AI assistant to run commands while keeping user approval and audit logs in place. Approved commands are stored persistently and can be revoked.
Key features
- 01User approval required for first-time commands
- 02Persistent storage of approved commands
- 03Audit logging of command execution
- 04Five-minute command timeout
- 05Revocation of command approvals
Use cases
- 01Letting an AI assistant run npm install in a project directory
- 02Reviewing the history of commands executed through the server
- 03Revoking approval for commands no longer needed
MCP support
This project is an MCP server that provides the execute_command and revoke_command_approval tools and the commands://approved resource to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEDynamic Shell Command MCP Server
A Model Context Protocol (MCP) server that enables secure execution of shell commands with a dynamic approval system. This server allows running arbitrary commands while maintaining security through user approval and audit logging.
Features
- 🔐 Dynamic command approval system
- 📝 Persistent storage of approved commands
- 📊 Comprehensive audit logging
- ⏱️ Command timeout protection
- 🔄 Command revocation capability
Installation
- Clone this repository:
git clone <repository-url>
cd dynamic-shell-server
- Create a virtual environment and activate it:
python -m venv venv
source venv/bin/activate # On Windows use: venv\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
Usage
Standalone Mode
Run the server directly:
python dynamic_shell_server.py
Claude Desktop Integration
-
Open your Claude Desktop configuration:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
-
Add the server configuration:
{
"mcpServers": {
"shell": {
"command": "/absolute/path/to/.venv/bin/python",
"args": ["/absolute/path/to/dynamic_shell_server.py"]
}
}
}
- Restart Claude Desktop
Command Approval Process
When running a command for the first time, you'll be prompted with:
Command Approval Required
Command: <command>
Arguments: <args>
This command has not been previously approved. Do you want to:
1. Allow this command once
2. Allow this command and remember for future use
3. Deny execution
Please choose an option (1-3):
Available Tools
-
execute_command: Execute a shell command- Parameters:
command: The command to executeargs: Optional list of command arguments
- Parameters:
-
revoke_command_approval: Revoke approval for a previously approved command- Parameters:
command: The command to revoke approval for
- Parameters:
Available Resources
commands://approved: Lists all approved commands with their approval dates
Data Storage
The server stores its data in ~/.config/mcp-shell-server/:
approved_commands.json: List of approved commands and their approval datesaudit.log: Detailed execution history of all commands
Security Features
- User approval required for first-time command execution
- Persistent storage of approved commands
- Comprehensive audit logging
- 5-minute command timeout
- No shell execution (prevents injection attacks)
- Command revocation capability
Example Usage
Through Claude Desktop:
Human: Run 'npm install' in my project directory
Assistant: I'll help you run that command. Since this is the first time running 'npm install', you'll need to approve it.
[Command approval prompt appears]
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.