Command Line Interface Enhancer
Enables execution of shell commands, directory navigation, and interactive program automation through an enhanced command-line interface. Provides tools for running commands, managing working directories, and handling interactive programs using expect/send sequences.
README
Command Line Interface Enhancer (command_cli_enh.py)
This script provides an enhanced command-line interface for interacting with the Gemini API, leveraging FastMCP for tool access.
Usage
python3 command_cli_enh.py [OPTIONS]
Parameters
-p,--prompt <TEXT>: Provide the prompt text directly from the command line.-f,--file <PATH>: Specify the path to a text file containing the prompt.
Note: You must provide either --prompt or --file, but not both.
Available MCP Tools
Available Tools Summary
--- Tool 1/4 ---
- Name: run_command
- Purpose: Run a shell command on the local machine and get the output. Args: command: The shell command to execute. workdir: The working directory for the command. If None, uses the current directory. stdin: Optional stdin to pipe into the command. Returns: A dictionary containing the command's output, exit code, and error status.
- Inputs:
- command*: <string>
- workdir: <string | null>
- stdin: <string | null>
--- Tool 2/4 ---
- Name: get_current_dir
- Purpose: Get the current working directory returns str -> directory ( ex "/home/user1"
- Inputs: (None)
--- Tool 3/4 ---
- Name: change_dir
- Purpose: Change the directory to specified string relative and absolute paths are supported If error - will return string "error: invalid directory"
- Inputs:
- c_dir*: <string>
--- Tool 4/4 ---
- Name: run_expect_script
- Purpose: Run a program with a sequence of expect/send actions for programs that are interactive. Programs that require inputs. important: do not send carriage return or line feed with text on send. Args: program: The command to run (e.g. "python3 myscript.py"). Can be any command actions: A list of dicts, e.g. [{"action": "expect", "text": "foo"}, {"action":"send","text":"bar"}] Returns: The output from the interaction.
- Inputs:
- program*: <string>
- actions*: <array>
############################## resouces: [Resource(name='system_info', title=None, uri=AnyUrl('resource://system_info'), description='Provides basic information about the host operating system.', mimeType='text/plain', size=None, icons=None, annotations=None, meta={'_fastmcp': {'tags': []}})]
| File | Purpose |
|---|---|
| LICENSE | Contains the MIT License, granting permission to use, copy, modify, and distribute the software. |
| README.md | Provides a general overview of the project, its purpose, and usage instructions. |
| command_cli_enh.py | A command-line interface (CLI) for interacting with the mcp_command_server_enh.py script. |
| config.toml | Configuration file for the project, likely containing settings for the server and CLI. |
| item.py | random vegetable and fruit generator - used for demonstrarion. |
| list.py | command to list mcp tools using list tools . |
| mcp_command_server_enh.py | The main command server script that listens for and executes commands. |
| orig.py | Appears to be an earlier version or a related script. |
| pexpect_auto.py | Uses the pexpect library to automate interactions with another program. |
| pythagoras.py | A script related to the Pythagorean theorem, possibly for testing or demonstration. |
| test1.txt - test7.txt | Test promptSs used for testing the functionality of the scripts. |
| test_float_input.py | A script for testing floating-point number input. |
| test_input.py | A script for testing general input. |
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。