MCP Agent Typescript Port

🚀 MCP Agent TypeScript Port

The TypeScript port of the MCP (Model Context Protocol) Agent is a powerful and type - safe implementation of the MCP Agent system. It offers a flexible framework for building intelligent context - aware agents with advanced workflow management, logging, and execution capabilities.

🚀 Quick Start

Create a Workflow

import { BaseWorkflow } from '@waldzell/mcp-agent-ts';

class MyDataProcessingWorkflow extends BaseWorkflow {
  constructor() {
    super('my-workflow', 'Data Processing');

    this.addStep({
      id: 'extract',
      name: 'Data Extraction',
      execute: async (context) => {
        // Implement data extraction logic
        return { data: ['item1', 'item2'] };
      }
    });

    this.addStep({
      id: 'transform',
      name: 'Data Transformation',
      execute: async (context) => {
        // Implement data transformation logic
        return { transformedData: ['ITEM1', 'ITEM2'] };
      }
    });
  }
}

async function runWorkflow() {
  const workflow = new MyDataProcessingWorkflow();
  const results = await workflow.execute();
  console.log(results);
}

Logging

import { debug, info, warn, error } from '@waldzell/mcp-agent-ts';

// Use different log levels
debug('Debug information', { userId: 123 });
info('System has started');
warn('Potential issue detected');
error('Critical error occurred');

CLI Usage

# Start the MCP Agent
npx mcp-agent start

# List available tools
npx mcp-agent list-tools

# Set the log level
npx mcp-agent log-level debug

Executor Usage

import { BaseExecutor, Task } from '@waldzell/mcp-agent-ts';

const executor = new BaseExecutor();

executor.run({
  id: 'task-1',
  name: 'Sample Task',
  command: 'echo "Hello MCP Agent!"'
}).then(() => {
  console.log('Task completed');
});

✨ Features

• 🚀 Modular Architecture

  • Comprehensive TypeScript implementation
  • Flexible and extensible design
  • Type - safe interfaces

• 📊 Advanced Workflow Management

  • Step - based workflow execution
  • Concurrent task processing
  • Detailed context tracking

• 🔍 Powerful Logging System

  • Configurable log levels
  • Context - rich logging
  • Log export functionality

• 🧰 Flexible Executor

  • Task queuing
  • Timeout handling
  • Concurrent task management

• 🖥️ CLI Support

  • Command - line interface
  • Easy agent management

📦 Installation

Install via Smithery

To automatically install the MCP Agent TypeScript port for Claude Desktop via Smithery:

npx -y @smithery/cli install @waldzellai/mcp-agent-ts --client claude

Manual Installation

npm install @waldzell/mcp-agent-ts

📚 Documentation

Configuration

The MCP Agent supports the following configuration methods:

• Environment Variables: Configure the agent's behavior by setting environment variables.
• Configuration Files: Use JSON or YAML files for configuration.
• Programmatic Configuration: Configure agent options directly in the code.

Project Status

This project is currently in the early development stage. Contributions, issue reports, and suggestions are welcome.

Original Project Link

https://github.com/lastmile-ai/mcp-agent

📄 License

The MCP Agent is distributed under the MIT License.