MCP Terminal & Git Server

MCP Terminal & Git Server

Enables execution of terminal commands, git operations, and automated setup of React, Vue, and Next.js projects with VSCode integration.

Category
Visit Server

README

mcp-terminal

MCP server for git and terminal access

Features

This MCP server provides the following tools:

  • execute_command: Execute a terminal command in a specified directory.
  • git_clone: Clone a git repository to a specified location.
  • install_react_project: Create a new React project using Vite.
  • install_vue_project: Create a new Vue project using Vite.
  • install_next_project: Create a new Next.js project.
  • open_in_vscode: Open a directory or file in VSCode.
  • check_directory: Check if a directory exists and list its contents.

Prerequisites

Installation

  1. Clone the repository (if you haven't already):
    git clone https://github.com/AbdurRaahimm/mcp-git-terminal-server.git mcp-terminal
    cd mcp-terminal
    
  2. Install dependencies:
    npm install
    

Usage

  1. Build the server:

    npm run build
    
  2. Start the server:

    npm run start
    

    Alternatively, you can use the development script which builds and then starts the server:

    npm run dev
    

    The server will then be running on stdio, ready to accept MCP requests from a compatible client.

    To configure this server with an MCP client, you might need to specify the path to the built index.js file (e.g., dist/index.js in this project's root) and the command to run it (e.g., node). Refer to your MCP client's documentation for specific instructions.

Available Tools

Here's a more detailed look at the available tools and their parameters:

execute_command

Execute a terminal command in a specified directory.

  • Input Schema:
    • command (string, required): The command to execute (e.g., 'npm install', 'ls -la').
    • cwd (string, optional): Working directory for the command (defaults to current directory).

git_clone

Clone a git repository to a specified location.

  • Input Schema:
    • repositoryUrl (string, required): Git repository URL.
    • destination (string, required): Destination path where to clone the repository.
    • openInVSCode (boolean, optional): Open the cloned repository in VSCode (default: false).

install_react_project

Create a new React project using Vite and open it in VSCode.

  • Input Schema:
    • projectName (string, required): Name of the React project.
    • destination (string, required): Directory where to create the project (e.g., ~/Desktop).
    • template (string, optional, enum: ["react", "react-ts", "react-swc", "react-swc-ts"]): Vite template to use (default: react-ts).
    • installDependencies (boolean, optional): Install dependencies after creating project (default: true).

install_vue_project

Create a new Vue project using Vite and open it in VSCode.

  • Input Schema:
    • projectName (string, required): Name of the Vue project.
    • destination (string, required): Directory where to create the project (e.g., ~/Desktop).
    • template (string, optional, enum: ["vue", "vue-ts"]): Vite template to use (default: vue-ts).
    • installDependencies (boolean, optional): Install dependencies after creating project (default: true).

install_next_project

Create a new Next.js project and open it in VSCode.

  • Input Schema:
    • projectName (string, required): Name of the Next.js project.
    • destination (string, required): Directory where to create the project (e.g., ~/Desktop).
    • typescript (boolean, optional): Use TypeScript (default: true).
    • installDependencies (boolean, optional): Install dependencies after creating project (default: true).

open_in_vscode

Open a directory or file in VSCode.

  • Input Schema:
    • path (string, required): Path to open in VSCode.

check_directory

Check if a directory exists and list its contents.

  • Input Schema:
    • path (string, required): Directory path to check.

License

This project is licensed under the MIT License. (As specified in package.json)

Usage

{
  "mcpServers": {
    "git-terminal": {
      "command": "node",
      "args": ["/path/to/mcp-git-terminal/dist/index.js"]
    }
  }
}

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured