mcpField
M
mcp-task

mcp-task

Local
github.com/mikaelmorvanProductivity3Updated 81w ago

About mcp-task

mcp-task is a Redis-backed task management MCP server for simple task tracking and demonstrations of the MCP Go library. It supports assignment, status filtering, and title search, and is explicitly not intended for production use.

Key features

  1. 01Create, update, and delete tasks
  2. 02Assign tasks to users
  3. 03Mark tasks complete
  4. 04Filter tasks by status
  5. 05Search tasks by title

Use cases

  1. 01Manage everyday tasks through an MCP client
  2. 02Demonstrate task management with the MCP Go library

MCP support

The server exposes task management capabilities to MCP clients, including creating, updating, deleting, and assigning tasks. The README describes connecting through an SSE URL.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-task

MCP server demoing a task management.

I use the MCP Go library of MegaGrindStone to create a simple task management server. It uses Redis as a backend for storing tasks.

The purpose of this project is to demonstrate the use of the MCP Go library and provide a simple task management solution. It's not intended for production use.

Getting Started

Prerequisites

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

Features

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

Installation

You can launch the server using Docker or run it locally.

Docker
docker-compose up

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

Local

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

go run main.go

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

How to interact with the server

Using MCP client

I use the MCP Web UI of MegaGrindStone to interact with the server. You can use the web UI to create, update, delete tasks, and assign them to users. The web UI is a simple and easy-to-use interface for managing tasks.

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

port: 8080
logLevel: debug # Choose one of the following: debug, info, warn, error, default to info
logMode: text # Choose one of the following: json, text, default to text
systemPrompt: You are a helpful assistant.
titleGeneratorPrompt: Generate a title for this chat with only one sentence with maximum 5 words.
# Choose one of the following LLM providers: ollama, anthropic
llm:

  # anthropic
  apiKey: XXX# Default to 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

Note on Anthropic Client

Antropic Client do not support SSE server for now.

Using the MCP client

The MCP client (MCP Web UI) is connected to Anthropic's Claude 3 model. You can use the web UI to create, update, delete tasks, and assign them to users. The web UI is a simple and easy-to-use interface for managing tasks.

Prompt example

Give me my tasks for today
Create a task to buy groceries
Create a task to go to the restaurant "Chez Michel" tomorrow at 7pm

Contributing

If you want to contribute to this project, feel free to open an issue or a pull request. I welcome any contributions, whether it's bug fixes, new features, or improvements to the documentation.

License

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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.