Public

milkosten_task-mcp-server

Try Now

2025-03-07

Mirror ofhttps://github.com/milkosten/task-mcp-server

3 years

Works with Finder

0

Github Watches

0

Github Forks

0

Github Stars

Task API Server - MCP TypeScript Implementation

A Model Context Protocol (MCP) implementation for Task Management API written in TypeScript. This project serves as both a reference implementation and a functional task management server.

Overview

This MCP server connects to an external Task API service and provides a standardized interface for task management. It supports two runtime modes:

STDIO Mode: Standard input/output communication for CLI-based applications and AI agents
HTTP+SSE Mode: Web-accessible server with Server-Sent Events for browser and HTTP-based clients

The server offers a complete set of task management operations, extensive validation, and robust error handling.

Features

Task Management Operations:
- List existing tasks with filtering capabilities
- Create new tasks with customizable properties
- Update task details (description, status, category, priority)
- Delete tasks when completed or no longer needed
Dual Interface Modes:
- STDIO protocol support for command-line and AI agent integration
- HTTP+SSE protocol with web interface for browser-based access
MCP Protocol Implementation:
- Complete implementation of the Model Context Protocol
- Resources for task data structures
- Tools for task operations
- Error handling and informative messages
Quality Assurance:
- Comprehensive test client for validation
- Automatic server shutdown after tests complete
- Detailed validation of API responses

Getting Started

Prerequisites

Node.js 16.x or higher
npm or pnpm package manager

Installation

Clone the repository:

git clone https://github.com/yourusername/mcp-template-ts.git
cd mcp-template-ts

Install dependencies:
```
npm install
```
or using pnpm:
```
pnpm install
```

Create an .env file with your Task API credentials:

TASK_MANAGER_API_BASE_URL=https://your-task-api-url.com/api
TASK_MANAGER_API_KEY=your_api_key_here
TASK_MANAGER_HTTP_PORT=3000

Build the project:
```
npm run build
```

Running the Server

STDIO Mode (for CLI/AI integration)

npm start

node dist/index.js

HTTP Mode (for web access)

npm run start:http

node dist/http-server.js

By default, the HTTP server runs on port 3000. You can change this by setting the TASK_MANAGER_HTTP_PORT environment variable.

Testing

Run the comprehensive test suite to verify functionality:

npm test

This will:

Build the project
Start a server instance
Connect a test client to the server
Run through all task operations
Verify correct responses
Automatically shut down the server

Using the MCP Client

STDIO Client

To connect to the STDIO server from your application:

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
import * as path from 'path';

// Create transport
const transport = new StdioClientTransport({
  command: 'node',
  args: [path.resolve('path/to/dist/index.js')]
});

// Initialize client
const client = new Client(
  {
    name: "your-client-name",
    version: "1.0.0"
  },
  {
    capabilities: {
      prompts: {},
      resources: {},
      tools: {}
    }
  }
);

// Connect to server
await client.connect(transport);

// Example: List all tasks
const listTasksResult = await client.callTool({
  name: "listTasks",
  arguments: {}
});

// Example: Create a new task
const createTaskResult = await client.callTool({
  name: "createTask",
  arguments: {
    task: "Complete project documentation",
    category: "Documentation",
    priority: "high"
  }
});

// Clean up when done
await client.close();

HTTP Client

To connect to the HTTP server from a browser:

<!DOCTYPE html>
<html>
<head>
  <title>Task Manager</title>
  <script type="module">
    import { Client } from 'https://cdn.jsdelivr.net/npm/@modelcontextprotocol/sdk/dist/esm/client/index.js';
    import { SSEClientTransport } from 'https://cdn.jsdelivr.net/npm/@modelcontextprotocol/sdk/dist/esm/client/sse.js';

    document.addEventListener('DOMContentLoaded', async () => {
      // Create transport
      const transport = new SSEClientTransport('http://localhost:3000/mcp');
      
      // Initialize client
      const client = new Client(
        {
          name: "browser-client",
          version: "1.0.0"
        },
        {
          capabilities: {
            prompts: {},
            resources: {},
            tools: {}
          }
        }
      );

      // Connect to server
      await client.connect(transport);
      
      // Now you can use client.callTool() for tasks
    });
  </script>
</head>
<body>
  <h1>Task Manager</h1>
  <!-- Your interface elements here -->
</body>
</html>

Available Tools

listTasks

Lists all available tasks.

const result = await client.callTool({
  name: "listTasks",
  arguments: {
    // Optional filters
    status: "pending", // Filter by status
    category: "Work",  // Filter by category
    priority: "high"   // Filter by priority
  }
});

createTask

Creates a new task.

const result = await client.callTool({
  name: "createTask",
  arguments: {
    task: "Complete the project report",  // Required: task description
    category: "Work",                     // Optional: task category
    priority: "high"                      // Optional: low, medium, high
  }
});

updateTask

Updates an existing task.

const result = await client.callTool({
  name: "updateTask",
  arguments: {
    taskId: 123,                       // Required: ID of task to update
    task: "Updated task description",  // Optional: new description
    status: "done",                    // Optional: pending, started, done
    category: "Personal",              // Optional: new category
    priority: "medium"                 // Optional: low, medium, high
  }
});

deleteTask

Deletes a task.

const result = await client.callTool({
  name: "deleteTask",
  arguments: {
    taskId: 123  // Required: ID of task to delete
  }
});

Environment Variables

Variable	Description	Default
TASK_MANAGER_API_BASE_URL	URL for the external Task API	None (Required)
TASK_MANAGER_API_KEY	API key for authentication	None (Required)
TASK_MANAGER_HTTP_PORT	Port for the HTTP server	3000
PORT	Alternative port name (takes precedence)	None

Project Structure

mcp-template-ts/
├── dist/               # Compiled JavaScript files
├── src/                # TypeScript source files
│   ├── index.ts        # STDIO server entry point
│   ├── http-server.ts  # HTTP+SSE server entry point
│   ├── test-client.ts  # Test client implementation
├── .env                # Environment variables
├── package.json        # Project dependencies
├── tsconfig.json       # TypeScript configuration
└── README.md           # Project documentation

Development

Start the TypeScript compiler in watch mode:
```
npm run watch
```
Run tests to verify changes:
```
npm test
```

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

This project uses the @modelcontextprotocol/sdk for MCP protocol implementation
Built for integration with AI tooling and web applications

Reviews

2 (1)

user_y4U2dekL

2025-04-16

As a dedicated user of MCP applications, I highly recommend the milkosten_task-mcp-server by MCP-Mirror. This server has proven to be reliable, efficient, and integral to my workflow. The clear documentation and welcome message make it easy to get started. Its seamless integration into various projects is a major plus. Check it out [here](https://github.com/MCP-Mirror/milkosten_task-mcp-server) for a robust server application experience.