Smart Terminal MCP
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Smart Terminal MCPlist files in current directory"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
⚡ Published on PyPI and compatible with MCP clients that support the stdio transport.
Smart Terminal MCP
A lightweight Model Context Protocol (MCP) server built with FastMCP that enables AI assistants to interact with the local machine through terminal, filesystem, and Python execution tools.
The project was built to explore how MCP enables AI clients to securely communicate with external tools and automate local development workflows.
✨ Features
Execute terminal commands
Execute Python code snippets
Execute Python files
Read files
Write files
Search files using glob patterns
Search text inside files
Create folders
Delete folders
Lightweight and easy to extend
Published on PyPI
🛠️ Tech Stack
Python 3.13+
FastMCP
MCP
setuptools
📦 Installation
Using uv (Recommended)
uv add smart_terminal_mcpOr run it directly without installing:
uvx smart_terminal_mcpUsing pip
pip install smart_terminal_mcp🚀 MCP Server Configuration
Add the following configuration to your MCP client:
{
"smart_terminal": {
"transport": "stdio",
"command": "uvx",
"args": ["smart_terminal_mcp"]
}
}Once configured, the server can be used by MCP-compatible AI clients.
📂 Available Tools
Tool | Description |
bash | Execute terminal commands |
python_code | Execute Python code |
python_file | Execute a Python file |
read_file | Read the contents of a file |
write_file | Create or overwrite a file |
glob | Search files using glob patterns |
grep | Search text inside files |
create_folder | Create directories |
delete_folder | Delete directories |
📁 Project Structure
smart_terminal_mcp/
│
├── src/
│ └── smart_terminal_mcp/
│ ├── main.py
│ ├── tools.py
│
├── pyproject.toml
├── README.md
└── LICENSE🎯 Motivation
The goal of this project was to gain hands-on experience with the Model Context Protocol (MCP) by building a practical server that exposes useful local development tools to AI assistants.
It helped me understand:
MCP architecture
Tool registration
Python packaging
PyPI publishing
AI tool integration
Developer workflow automation
🔮 Roadmap
Future improvements include:
Workspace sandboxing
Safe command execution
File rename and copy operations
Git integration
Project scaffolding
Better error handling
Cross-platform support
Tool execution logging
⚠️ Disclaimer
This project is intended for educational and development purposes.
Some tools execute commands or modify files on the local machine. Only use this MCP server in trusted environments.
📜 License
MIT License
👨💻 Author
Mohd Bilal
If you found this project interesting, feel free to star the repository.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/BilalCodePhoenix/smart_terminal_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server