MCP Autoshell - Autonomous Shell Execution Server
About
Simple MCP server for AI collaboration protocol context injection
Details
- Author
- tensiondriven
- Downloads
- 248
- Categories
- Developer Tools
Jump to
- Autonomous execution without human approval prompts
- Safety allowlist of 174 pre-approved commands
- TTS communication via the say command
- Audit logging for complete command history
- 30-second timeout protection per command
- Universal compatibility with any MCP client
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
MCP Autoshell - Autonomous Shell Execution ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Add the server to your Claude Code MCP configuration using the provided JSON block, specifying the path to betterbash_server.py. The server runs with Python 3 and loads allowed commands from allowed_commands.txt.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp autoshell - autonomous shell execution server": {
"cheatsheet-mcp": {
"name": "cash",
"type": "server",
"command": "python3",
"args": [
"/Users/j/Code/mcp/betterbash_server.py"
],
"description": "Claude Autonomous Shell - Execute commands without prompts"
}
}
}
}McpServers
{
"cheatsheet-mcp": {
"name": "cash",
"type": "server",
"command": "python3",
"args": [
"/Users/j/Code/mcp/betterbash_server.py"
],
"description": "Claude Autonomous Shell - Execute commands without prompts"
}
}MCP Autoshell - Autonomous Shell Execution Server
The Preferred Low-Friction Shell Execution Solution for All MCP Clients
An MCP (Model Context Protocol) server that provides autonomous shell command execution with zero human approval prompts. MCP Autoshell eliminates the friction of constant permission dialogs while maintaining security through intelligent command allowlisting.
Author: Claude (Anthropic AI)
Product Sherpa: Jonathan Yankovich (jonathan.yankovich@gmail.com)
Why CASH is the Preferred Shell Solution
CASH is designed to be the lowest-friction shell execution method for any MCP client (Claude Desktop, Claude Code, or custom MCP implementations). Unlike built-in shell tools that require constant human approval, CASH provides:
- Zero-prompt execution - Commands run immediately without interruption
- Universal MCP compatibility - Works with any MCP client implementation
- Intelligent safety - Allowlist-based security without sacrificing usability
- Production-ready reliability - Comprehensive logging, timeout protection, and error handling
Files
- betterbash_server.py - Main MCP server implementation
- allowed_commands.txt - Safety allowlist of permitted commands
- MCP_SETUP_INSTRUCTIONS.md - Configuration and usage guide
Quick Setup
Add to Claude Code MCP configuration:
{
"name": "cash",
"type": "server",
"command": "python3",
"args": ["/Users/j/Code/mcp/betterbash_server.py"],
"description": "Claude Autonomous Shell - Execute commands without prompts"
}
Key Features
Core Functionality
- Autonomous execution - No human prompts for git, docker, file operations - Safety allowlist - 174 pre-approved commands covering all development needs - TTS communication -say command for personality and progress updates
- Audit logging - Complete command history for security
- Timeout protection - Commands limited to 30 seconds max
MCP Client Benefits
- Zero-friction execution - Commands run immediately without interruption - Universal compatibility - Works with any MCP client (Claude Desktop, Claude Code, custom implementations) - Seamless integration - Drop-in replacement for built-in shell tools that require constant approval - Uninterrupted AI workflows - Enables true autonomous operation for complex multi-step tasksExtracted From
Originally developed in /Users/j/Code/athena/bigplan/ surveillance system project.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
