claude-command-runner

M-Pineapple/claude-command-runner

3.4

If you are the rightful owner of claude-command-runner and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

Claude Command Runner is a powerful Model Context Protocol (MCP) server that bridges Claude Desktop and terminal applications, enabling seamless command execution with intelligent output retrieval and comprehensive v3.0 features.

Claude Command Runner revolutionizes the development workflow by allowing Claude to execute terminal commands directly from conversations, automatically capture output with intelligent timing, track command history and patterns, and maintain security with configurable policies. The v3.0 release introduces enhanced auto-retrieve capabilities with progressive delays and smart command detection, rock-solid stability with fixed server crashes, and persistent operation. It also integrates a SQLite database for command history and analytics, and offers a configuration system for customizable security and behavior settings. The server intelligently waits longer for compilation commands, ensuring comprehensive output retrieval. With multi-terminal support and command suggestions based on history, Claude Command Runner enhances productivity and streamlines command execution processes.

Features

  • Enhanced Auto-Retrieve: Progressive delays with smart command detection for different command types.
  • Rock-Solid Stability: Fixed server crashes and persistent operation.
  • Database Integration: SQLite command history and analytics.
  • Configuration System: Customizable security and behavior settings.
  • Build Intelligence: Automatically waits longer for compilation commands.

Usages

usage with claude desktop

{
  "claude-command-runner": {
    "command": "/path/to/claude-command-runner/.build/release/claude-command-runner",
    "args": ["--port", "9876"],
    "env": {}
  }
}

Tools

  1. execute_command

    Execute with manual output retrieval

  2. execute_with_auto_retrieve

    Execute with intelligent auto-retrieval

  3. get_command_output

    Manually retrieve command output

  4. preview_command

    Preview without executing

  5. suggest_command

    Get command suggestions