Alice MCP - Agile Task Management

What is Alice MCP - Agile Task Management?

Alice MCP - Agile Task Management is a lightweight, local server that supports agile task workflows within AI coding environments using the Model Context Protocol (MCP). It provides a backend for managing projects, tasks, epics, and messages locally on your machine, with project isolation to support multiple distinct software projects.

How to use Alice MCP - Agile Task Management?

Clone the repository, create and activate a Python virtual environment, and install dependencies from requirements.txt. You can run the server automatically via the provided scripts/start-alice-servers.sh wrapper script, or manually by starting the FastAPI backend with uvicorn app.main:app --reload. When using the MCP server tools, provide the project’s name (string) as the project_id argument; for direct API calls, use the internal numeric project ID.

Key features of Alice MCP - Agile Task Management

• Project Management: Create and manage distinct projects.
• Task & Epic Tracking: Organize work into tasks and epics.
• Message Logging: Attach messages or notes to specific tasks.
• Project Isolation: All data is scoped to a project.
• Local Operation: Runs entirely on your machine using SQLite.
• MCP Integration: Designed as a tool provider for MCP environments.

Use cases of Alice MCP - Agile Task Management

• Manage tasks and epics for multiple isolated software projects.
• Attach contextual notes or messages to individual tasks.
• Use as a local backend for AI coding assistants that support MCP.
• Organize agile work items without a cloud dependency.

FAQ from Alice MCP - Agile Task Management

What are the runtime dependencies?

Python 3, a virtual environment, and packages listed in requirements.txt. The server uses SQLite locally and requires no external database.

How does project isolation work?

Direct API endpoints use numeric project IDs in URL paths (e.g., /1/tasks/). When using the MCP server tools, you provide the project’s name as project_id, and the MCP server resolves it to the internal numeric ID.

Where is data stored?

All data is stored locally in a SQLite database file. No data is sent to external servers.

How do I interact with the API?

While the server is running, interactive API documentation is available at http://127.0.0.1:8000/docs (Swagger UI) or http://127.0.0.1:8000/redoc (ReDoc). You can also send direct HTTP requests to the endpoints listed in the README.

Does the server require authentication?

The README does not mention any authentication mechanism. The server runs locally on 127.0.0.1:8000 by default.