FastMCP Todo MCP server for AI agents

Omnispindle is a FastMCP-based todo management system that serves as a central hub for multi-project task coordination. It combines AI-powered task insights with a visual dashboard to help transform chaos into productivity, allowing AI agents to create, manage, and organize tasks across multiple projects.

Installation

Prerequisites

Docker (recommended for easiest setup)
Python 3.8+ (for local installation)
MongoDB
MQTT broker

Option 1: Docker Installation (Recommended)

git clone https://github.com/DanEdens/Omnispindle.git
cd Omnispindle
docker-compose up -d

Option 2: Local Installation

Clone the repository:

git clone https://github.com/DanEdens/Omnispindle.git
cd Omnispindle

Install with uv:

curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv
source .venv/bin/activate  # On Unix/macOS
uv pip install -r requirements.txt

Configure your environment:

cp .env.example .env
# Edit .env with your MongoDB and MQTT settings

Configuration

Create a .env file with your settings:

# MongoDB Configuration
MONGODB_URI=mongodb://localhost:27017
MONGODB_DB=todo_app
MONGODB_COLLECTION=todos

# MQTT Configuration
MQTT_HOST=localhost
MQTT_PORT=1883

# AI Integration (optional)
AI_API_ENDPOINT=http://localhost:1234/v1
AI_MODEL=qwen2.5-7b-instruct

MCP Integration with Claude Desktop

Docker Configuration

Add to your Claude Desktop claude_desktop_config.json:

{
  "mcpServers": {
    "omnispindle": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "--network", "host",
        "-e", "MONGODB_URI=mongodb://localhost:27017",
        "-e", "MONGODB_DB=swarmonomicon",
        "-e", "MQTT_HOST=localhost",
        "danedens31/omnispindle:latest"
      ]
    }
  }
}

Docker Compose Configuration

{
  "mcpServers": {
    "omnispindle": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "--env-file", "/path/to/your/.env",
        "--network", "omnispindle_default",
        "danedens31/omnispindle:latest"
      ]
    }
  }
}

Local Development Configuration

{
  "mcpServers": {
    "omnispindle": {
      "command": "python",
      "args": ["-m", "src.Omnispindle"],
      "cwd": "/path/to/Omnispindle",
      "env": {
        "MONGODB_URI": "mongodb://localhost:27017",
        "MONGODB_DB": "swarmonomicon",
        "MQTT_HOST": "localhost"
      }
    }
  }
}

Usage

Starting the MCP Server

# Development mode
python -m src.Omnispindle

# Production mode
uvicorn src.Omnispindle.server:app --host 0.0.0.0 --port 8000

Available MCP Tools

The server exposes these tools for AI agents:

add_todo_tool - Create new tasks with metadata
query_todos_tool - Search and filter tasks
update_todo_tool - Modify existing tasks
mark_todo_complete_tool - Complete tasks
list_project_todos_tool - Get tasks by project
add_lesson_tool - Capture lessons learned
search_lessons_tool - Query knowledge base
mqtt_publish_tool - Send real-time messages
mqtt_get_tool - Retrieve MQTT messages

Using MCP Tools (for AI Agents)

AI agents can call standardized MCP tools:

# Example: AI agent creating a todo
await add_todo_tool(
    description="Implement user authentication",
    project="Omnispindle",
    priority="High",
    target_agent="developer",
    metadata={"ticket": "AUTH-123", "tags": ["security", "backend"]}
)

# Example: AI agent querying todos
results = await query_todos_tool(
    query_or_filter="project:Omnispindle",
    fields_or_projection="all",
    limit=50
)

API Usage

from fastmcp import FastMCPClient

# Connect to Omnispindle
client = FastMCPClient("http://localhost:8000")

# Create a new todo
response = await client.call_tool("add_todo_tool", {
    "description": "Fix critical bug in authentication",
    "project": "Madness_interactive",
    "priority": "High"
})

# Get project todos
todos = await client.call_tool("list_project_todos_tool", {
    "project": "Omnispindle",
    "limit": 10
})

Node-RED Dashboard

Access the dashboard at http://localhost:1880/ui
Import flows from Todomill_projectorium/ExportedNodeRedTabs/
Configure MQTT connection to point to your Omnispindle instance

MQTT Event Streaming

# Subscribe to todo events
mosquitto_sub -t "omnispindle/todos/+/+"

# Publish todo creation request
mosquitto_pub -t "omnispindle/todos/create" -m '{
    "description": "Deploy to production",
    "project": "Omnispindle",
    "priority": "High"
}'

Integration Examples

Swarmonomicon Integration

# Omnispindle works with Swarmonomicon for distributed task processing
from swarmonomicon import TaskAgent

agent = TaskAgent("omnispindle-worker")
agent.register_mcp_server("http://localhost:8000")

# Agent can now create and manage todos via MCP
await agent.execute_task("create_todo", {
    "description": "Process data pipeline",
    "project": "Swarmonomicon"
})

GitHub Issues Sync

# Sync todos with GitHub issues
todo_id = await add_todo_tool(
    description="Fix authentication bug",
    project="Madness_interactive",
    metadata={"github_issue": 1234}
)

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "omnispindle" '{"command":"docker","args":["run","--rm","-i","--network","host","-e","MONGODB_URI=mongodb://localhost:27017","-e","MONGODB_DB=swarmonomicon","-e","MQTT_HOST=localhost","danedens31/omnispindle:latest"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "omnispindle": {
            "command": "docker",
            "args": [
                "run",
                "--rm",
                "-i",
                "--network",
                "host",
                "-e",
                "MONGODB_URI=mongodb://localhost:27017",
                "-e",
                "MONGODB_DB=swarmonomicon",
                "-e",
                "MQTT_HOST=localhost",
                "danedens31/omnispindle:latest"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "omnispindle": {
            "command": "docker",
            "args": [
                "run",
                "--rm",
                "-i",
                "--network",
                "host",
                "-e",
                "MONGODB_URI=mongodb://localhost:27017",
                "-e",
                "MONGODB_DB=swarmonomicon",
                "-e",
                "MQTT_HOST=localhost",
                "danedens31/omnispindle:latest"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect