Skip to main content

MCP server for intelligent task prioritization with Claude Desktop

Project description

TaskPriority MCP Server

MCP Version Python Version License PyPI npm Docker

An intelligent task prioritization server that integrates with Claude Desktop through the Model Context Protocol (MCP). TaskPriority helps you manage tasks efficiently by providing AI-powered analysis including priority scoring, time estimation, and similarity detection.

🌟 Features

  • AI-Powered Task Analysis: Automatic priority scoring (1-10), complexity assessment, and time estimation
  • Smart Task Management: Create, update, list, and delete tasks with full CRUD operations
  • Similarity Detection: Identifies duplicate and related tasks to prevent redundancy
  • Real-time Analysis: Get instant AI insights when creating or analyzing tasks
  • MCP Integration: Seamlessly works with Claude Desktop for natural language task management

📋 Prerequisites

  • Python 3.10 or higher
  • Claude Desktop (for MCP integration)
  • TaskPriority API key from taskpriority.ai

🚀 Quick Start

1. Install the Server

Choose one of these installation methods:

Option A: Install from PyPI (Recommended)

pip install taskpriority-mcp

Option B: Install from GitHub

pip install git+https://github.com/greenblat17/priority-mcp.git

Option C: Install from Source

git clone https://github.com/greenblat17/priority-mcp.git
cd mcp-priority
pip install -e .

2. Get Your API Key

  1. Sign up at taskpriority.ai
  2. Go to Settings → API Keys
  3. Create a new key (starts with tp_live_)

3. Configure Claude Desktop

Find your Claude Desktop 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

Add this configuration:

{
  "mcpServers": {
    "taskpriority": {
      "command": "taskpriority-mcp",
      "env": {
        "TASKPRIORITY_API_KEY": "tp_live_your_api_key_here"
      }
    }
  }
}

4. Restart Claude Desktop

Completely quit and restart Claude Desktop for the changes to take effect.

💡 Usage

Once configured, you can use natural language commands in Claude Desktop:

Creating Tasks

"Create a task to implement user authentication"
"Add a bug report about the login page not loading"
"New task: Improve database query performance"

Listing Tasks

"Show me all my pending tasks"
"List high-priority bugs"
"What tasks are in progress?"

Updating Tasks

"Mark task 123e4567 as completed"
"Update the authentication task to in-progress"
"Change the priority of the database task"

Getting AI Analysis

"Analyze task 123e4567"
"What's the time estimate for the authentication task?"
"Show me tasks similar to implementing payment processing"

🛠️ Available MCP Tools

create_task

Creates a new task with automatic AI analysis.

Parameters:

  • description (required): Task description
  • source (optional): Origin of the task (default: "internal")
  • customer_info (optional): Additional context

list_tasks

Lists tasks with filtering options.

Parameters:

  • status (optional): Filter by status (pending, in_progress, completed, blocked)
  • category (optional): Filter by category (bug, feature, improvement, business, other)
  • limit (optional): Number of results (default: 50, max: 100)
  • offset (optional): Pagination offset (default: 0)

get_task_details

Retrieves complete information about a specific task.

Parameters:

  • task_id (required): UUID of the task

update_task

Updates an existing task.

Parameters:

  • task_id (required): UUID of the task
  • status (optional): New status
  • description (optional): Updated description
  • customer_info (optional): Updated customer information

delete_task

Deletes a task permanently.

Parameters:

  • task_id (required): UUID of the task

get_ai_analysis

Gets or waits for AI analysis of a task.

Parameters:

  • task_id (required): UUID of the task
  • timeout (optional): Max seconds to wait for analysis (default: 30)

🔧 Configuration

Environment Variables

Variable Description Default Required
TASKPRIORITY_API_KEY Your TaskPriority API key - Yes
TASKPRIORITY_API_URL TaskPriority API base URL https://api.taskpriority.ai No
TASKPRIORITY_API_VERSION API version v1 No
TASKPRIORITY_TIMEOUT Request timeout in seconds 30 No
DEBUG_MODE Enable debug logging false No

Advanced Configuration

For advanced configuration options, see the Configuration Guide.

📚 Documentation

🤝 Contributing

Contributions are welcome! Please read our Contributing Guide for details on our code of conduct and the process for submitting pull requests.

📄 License

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

🙏 Acknowledgments

📞 Support


Made with ❤️ by the TaskPriority team

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

taskpriority_mcp-1.1.0.tar.gz (80.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

taskpriority_mcp-1.1.0-py3-none-any.whl (25.0 kB view details)

Uploaded Python 3

File details

Details for the file taskpriority_mcp-1.1.0.tar.gz.

File metadata

  • Download URL: taskpriority_mcp-1.1.0.tar.gz
  • Upload date:
  • Size: 80.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.9

File hashes

Hashes for taskpriority_mcp-1.1.0.tar.gz
Algorithm Hash digest
SHA256 50874501ea91bc5c25751b27dff4a2b1a0e84468aef87cda334efe59463ffd5c
MD5 6aa10dfffac8fac76646fd4cdf06fc52
BLAKE2b-256 f32e618e07c94e0ad1a8a5423b0c794d5a6e2ba063df78824eb3e05602734d20

See more details on using hashes here.

File details

Details for the file taskpriority_mcp-1.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for taskpriority_mcp-1.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d23c14bc3d6aea2363d811b964e33956f5546673ef1a49a40f992e80206348e8
MD5 0964857709ce336551fb26a572f222d2
BLAKE2b-256 23b347ffaa33b75d77cee35db8a87f9eb312cdae9262b1fa0c3d641c982c189b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page