MCP ExplorerExplorer

Mcp Server Project Ts

@erniebrodeuron 22 days ago
1 MIT
FreeCommunity
AI Systems
MCP Server for tracking TypeScript/JavaScript project changes and dependencies.

Overview

What is Mcp Server Project Ts

mcp-server-project-ts is a Model Context Protocol (MCP) compliant server designed for tracking changes and managing dependencies in TypeScript/JavaScript projects. It allows AI agents to monitor file modifications without storing their content.

Use cases

Use cases include monitoring changes in large codebases, managing package dependencies in web applications, executing npm scripts during development, and providing project status updates to AI agents.

How to use

To use mcp-server-project-ts, you can run it directly with npx for a quick start: npx mcp-server-project-ts --workspaceRoot /path/to/your/project. Alternatively, you can install it globally using npm and run it from anywhere.

Key features

Key features include file change tracking, NPM dependency management, script execution with real-time output, comprehensive project status information, compliance with MCP standards, and a lightweight design that only tracks changes without storing file content.

Where to use

mcp-server-project-ts is ideal for TypeScript and JavaScript development environments, particularly in projects that require efficient change tracking and dependency management.

Content

MCP Project Change Tracker

A Model Context Protocol (MCP) compliant server for TypeScript/JavaScript project change tracking and dependency management.

Overview

This MCP server provides AI agents with structured tools to track file changes and manage dependencies in TypeScript/JavaScript projects. It follows the change notification pattern - tracking which files have changed without storing their content, allowing agents to read files themselves when needed.

🚀 Key Features

  • File Change Tracking: Monitor TypeScript/JavaScript file modifications
  • NPM Dependency Management: Install, uninstall, update, and audit packages
  • Script Execution: Run npm scripts with real-time output
  • Project Status: Get comprehensive project state information
  • MCP Compliant: Works with any MCP-compatible AI client
  • Lightweight: Only tracks changes, doesn’t store file content

🛠️ Available Tools

Tool Description
get_project_status Get project status with changed files and dependencies
refresh_changes Clear change tracking state
install_dependency Install npm packages (dev/prod)
uninstall_dependency Remove npm packages
update_dependency Update specific packages
check_outdated List outdated dependencies
run_npm_script Execute package.json scripts
list_scripts Show available npm scripts
npm_audit Security vulnerability audit

📖 View detailed examples and API reference →

📦 Installation

Prerequisites

  • Node.js 20+
  • npm (comes with Node.js)
  • A TypeScript/JavaScript project

Quick Start with npx (Recommended)

# Run directly with npx - no installation needed!
npx mcp-server-project-ts --workspaceRoot /path/to/your/project

Alternative: Global Installation

# Install globally for repeated use
npm install -g mcp-server-project-ts

# Then run anywhere
mcp-server-project --workspaceRoot /path/to/your/project

🔧 Usage

VS Code Integration

Add to your VS Code settings or MCP configuration:

{
  "mcpServers": {
    "mcp-server-project-ts": {
      "command": "npx",
      "args": [
        "mcp-server-project-ts",
        "--workspaceRoot",
        "${workspaceFolder}"
      ]
    }
  }
}

Claude Desktop Integration

Add to your Claude Desktop configuration file:

{
  "mcpServers": {
    "mcp-server-project-ts": {
      "command": "npx",
      "args": [
        "mcp-server-project-ts",
        "--workspaceRoot",
        "/path/to/your/project"
      ]
    }
  }
}

🏗️ Development

# Development mode with auto-restart
npm run dev -- --workspaceRoot .

# Build for production
npm run build

# Run tests
npm test

🎯 Why MCP?

This server follows the Model Context Protocol specification, providing:

  • Standardization: Works with any MCP-compatible client
  • Discoverability: Tools are self-describing with schemas
  • Type Safety: Input validation via JSON schemas
  • Documentation: Built-in tool descriptions for AI agents
  • Interoperability: Part of the growing MCP ecosystem

📄 License

MIT License - see LICENSE file for details.

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests if applicable
  5. Submit a pull request

📚 Documentation

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers