mcpField
M
MCP Autoshell - Autonomous Shell Execution Server

MCP Autoshell - Autonomous Shell Execution Server

Local
github.com/tensiondrivenDeveloper Tools1Updated 73w ago
Repository

About MCP Autoshell - Autonomous Shell Execution Server

MCP Autoshell is an MCP server that lets AI clients execute shell commands without per-command approval prompts. It uses an allowlist and includes audit logs and timeout protection for command execution.

Key features

  1. 01Shell command execution without approval prompts
  2. 02Allowlist of permitted commands
  3. 03Command history audit logging
  4. 04Execution timeout protection
  5. 05TTS progress messages via say

Use cases

  1. 01Running approved shell commands in AI workflows
  2. 02Automating multi-step development tasks
  3. 03Reviewing command history for auditing

MCP support

Provides MCP clients with autonomous shell command execution. Commands are constrained by an allowlist, with audit logging and timeout protection.

#mcp#autonomous-shell#ai-collaboration

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

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 ([email protected])

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 tasks

Extracted From

Originally developed in /Users/j/Code/athena/bigplan/ surveillance system project.

Comments

Markdown supported

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.