MCP Terminal Tools
Yaswanth-ampolu
README
MCP Terminal Tools
A cross-platform Model Context Protocol (MCP) server for terminal access and system tools. This package allows AI assistants like Claude to interact with your local system.
Features
- Run shell commands
- Execute Python scripts
- List directory contents
- Copy files
- Create files and directories
- Cross-platform support (Windows, macOS, Linux)
- Works with Claude Desktop and other MCP-compatible assistants
Installation
Global Installation (Recommended)
# Install globally via npm
npm install -g github:Yaswanth-ampolu/smithery-mcp-server
# Start the server
mcp-terminal
Local Installation
# Clone the repository
git clone https://github.com/Yaswanth-ampolu/smithery-mcp-server.git
cd smithery-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
# Start the server
npm start
Configuring Claude Desktop
- Open Claude Desktop
- Go to Settings → Model Context Protocol
- Add this configuration:
{
"mcpServers": {
"terminal": {
"url": "http://localhost:8080/sse",
"command": "terminal"
}
}
}
- Save and restart Claude Desktop
- Test by asking Claude: "terminal ls" or "terminal echo hello"
Environment Variables
Create a .env
file to customize settings:
# Server settings
SERVER_NAME=MCP System Tools
SERVER_VERSION=1.0.0
PORT=8080
# Python interpreter path (will default to platform-appropriate value if not set)
PYTHON_PATH=
# Default workspace directory (will be auto-determined if not specified)
# DEFAULT_WORKSPACE=C:\path\to\workspace # Windows
# DEFAULT_WORKSPACE=/path/to/workspace # Mac/Linux
# Server binding
MCP_SERVER_HOST=0.0.0.0
MCP_SERVER_PORT=8080
Available Tools
Tool | Description |
---|---|
runShellCommand |
Run a shell command and return its output |
runPythonFile |
Execute a Python script and return its output |
readDirectory |
List files and folders in a directory |
copyFile |
Copy a file from one location to another |
createFile |
Create a new file with the specified content |
Workspace Directory
The server uses a workspace directory for file operations:
- If
DEFAULT_WORKSPACE
is set in.env
, that location is used - Otherwise, it looks for a
workspace
folder in the current directory - If not found, it creates an
mcp-workspace
folder on your Desktop - If Desktop isn't available, it creates it in your home directory
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.