mlflowMCPServer
If you are the rightful owner of mlflowMCPServer and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
This project provides a natural language interface to MLflow via the Model Context Protocol (MCP).
MLflow MCP Server is a project that enables users to interact with their MLflow tracking server using natural language queries. It consists of two main components: the MLflow MCP Server, which connects to the MLflow tracking server and exposes its functionality through MCP, and the MLflow MCP Client, which provides a conversational AI interface to interact with the server. This setup allows users to manage and explore their machine learning experiments and models more intuitively. The server supports natural language queries, model registry exploration, experiment tracking, and system information retrieval. It requires Python 3.8+, a running MLflow server, and an OpenAI API key for the LLM.
Features
- Natural Language Queries: Ask questions about your MLflow tracking server in plain English.
- Model Registry Exploration: Get information about your registered models.
- Experiment Tracking: List and explore your experiments and runs.
- System Information: Get status and metadata about your MLflow environment.
Tools
list_models
Lists all registered models in the MLflow model registry.
list_experiments
Lists all experiments in the MLflow tracking server.
get_model_details
Gets detailed information about a specific registered model.
get_system_info
Gets information about the MLflow tracking server and system.
