label-studio-mcp-server
This project is a Model Context Protocol server designed to facilitate interactions with Label Studio for managing labeling projects and tasks. It allows for natural language and structured communication through an MCP client, providing features for project and task management and prediction integration.
Overview
This project provides a Model Context Protocol (MCP) server for interacting with a Label Studio instance. It enables management of labeling projects, tasks, and predictions using natural language or structured calls from MCP clients. Key features include project management, task management, prediction integration, and SDK integration. Prerequisites include a running Label Studio instance, an API key, and a Python environment.
Features
- Project Management: Create, update, list, and view project details.
- Task Management: Import tasks, list project tasks, and retrieve task data/annotations.
- Prediction Integration: Add model predictions to tasks.
Installation
Clone the repository, navigate to the directory, install dependencies, and configure the server using environment variables or an MCP client configuration file.
Running the Server
Run the server using Python with appropriate options for transport, port, and host settings.