MCP Task

🚀 Simple Task Management Server Demo

This is a simple demonstration of a task management server created using the MCP Go library developed by MegaGrindStone. It uses Redis as the backend to store tasks. The project aims to showcase the use of the MCP Go library and provide a straightforward task - management solution. Note that this project is not intended for production environments.

🚀 Quick Start

Prerequisites

• Go 1.18 or higher
• Redis server (included in the docker - compose file)

✨ Features

• Create, update, and delete tasks
• Assign tasks to users
• Mark tasks as completed
• Filter tasks by status
• Search tasks by title

📦 Installation

You can run the server using Docker or locally.

Docker

docker-compose up

You can access the server at http://localhost:8090/sse.

Local

Configure the config.json file according to your needs. You can use the provided config.example.json file as a template. You must run a Redis server locally.

go run main.go

You can access the server at http://localhost:8090/sse.

💻 Usage Examples

Basic Usage

Interacting with the Server Using the MCP Client

I used MegaGrindStone's MCP Web interface to interact with the server. You can use the web interface to create, update, and delete tasks, and assign them to users. The web interface is an easy - to - use task management interface.

To declare the MCP server, you can use the following configuration file:

port: 8080
logLevel: debug # Choose one: debug, info, warn, error, default is info
logMode: text # Choose one: json, text, default is text
systemPrompt: You are a helpful assistant.
titleGeneratorPrompt: Generate a title with only one sentence and no more than 5 words.
# Choose one of the following LLM providers: ollama, anthropic
llm:

  # anthropic
  apiKey: XXX# Defaults to getting from the environment variable ANTHROPIC_API_KEY
  model: claude-3-7-sonnet-20250219
  provider: anthropic
  # mistral
  # apiKey: XXXX
  # endpoint: https://api.mistral.ai/v1
  # model: mistral-large-latest
  maxTokens: 1000


mcpSSEServers:
  mcp-task-server:
    url: http://localhost:8090/sse
    maxPayloadSize: 1048576 # 1MB

Advanced Usage

Note for the Anthropic Client

Currently, the Anthropic client does not support SSE servers.

Using the MCP Client

The MCP client (MCP Web interface) connects to Anthropic's Claude 3 model. You can use the web interface to create, update, and delete tasks, and assign them to users. The web interface is an easy - to - use task management interface.

Usage Examples

Give me today's work tasks

Create a task to buy groceries

Create a task to go to the restaurant "Chez Michel" at 7 pm tomorrow

🤝 Contribution Guidelines

If you'd like to contribute to this project, feel free to open an issue or submit a pull request. I welcome all types of contributions, whether it's bug fixes, new features, or documentation improvements.

📄 License

This project is licensed under the MIT License. For more details, please refer to the LICENSE file.