MCP.so
Sign In

MCP Autoshell - Autonomous Shell Execution Server

@tensiondriven

Repository

About MCP Autoshell - Autonomous Shell Execution Server

Simple MCP server for AI collaboration protocol context injection

#mcp#autonomous-shell#ai-collaboration

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "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"
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Autoshell - Autonomous Shell Execution Server?

MCP Autoshell is an MCP server that provides autonomous shell command execution with zero human approval prompts. It uses an allowlist-based security model to maintain safety while eliminating constant permission dialogs, designed for MCP clients like Claude Desktop or Claude Code.

How to use MCP Autoshell - Autonomous Shell Execution Server?

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.

Key features of MCP Autoshell - Autonomous Shell Execution Server

  • 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

Use cases of MCP Autoshell - Autonomous Shell Execution Server

  • Automating git operations without interruption
  • Executing Docker commands in multi-step workflows
  • Performing file operations autonomously
  • Enabling complex multi-step AI tasks that require shell access
  • Building uninterrupted AI-driven development pipelines

FAQ from MCP Autoshell - Autonomous Shell Execution Server

What is the difference between MCP Autoshell and built-in shell tools?

Built-in shell tools require constant human approval; MCP Autoshell executes commands immediately with zero prompts, using an allowlist for safety.

What commands are allowed?

A safety allowlist of 174 pre-approved commands is provided in allowed_commands.txt. You can customize this list.

Is there a timeout for command execution?

Yes, commands are limited to 30 seconds maximum.

What dependencies are required?

The server requires Python 3 to run.

Does it support text-to-speech (TTS)?

Yes, it includes TTS communication using the say command for personality and progress updates.

Frequently asked questions

What is the difference between MCP Autoshell and built-in shell tools?

Built-in shell tools require constant human approval; MCP Autoshell executes commands immediately with zero prompts, using an allowlist for safety.

What commands are allowed?

A safety allowlist of 174 pre-approved commands is provided in `allowed_commands.txt`. You can customize this list.

Is there a timeout for command execution?

Yes, commands are limited to 30 seconds maximum.

What dependencies are required?

The server requires Python 3 to run.

Does it support text-to-speech (TTS)?

Yes, it includes TTS communication using the `say` command for personality and progress updates.

Comments

Basic information

Category

Developer Tools

Transports

stdio

Author

tensiondriven

More Developer Tools MCP servers

Reelier

Maxime Houle

Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.

LocalCan

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

82

AptiBuild AI — Career Intelligence

ParklandBuilds

AptiBuild AI — Career Intelligence MCP Server Structured career decision scaffolding for AI agents. Provides personality-conditioned business idea generation, official BLS OEWS wage data, FRED labor market signals, and

Repo Test Architect

RepoAssay

Local-first, read-only MCP server for evidence-backed repository test architecture audits and test planning.

Foremerge

naw103

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

50