"MLflow" matching MCP servers:

A natural language interface for MLflow that allows users to query and manage their machine learning experiments and models using plain English through the Model Context Protocol.

Enables financial agent workflows to perform agentic retrieval over SEC filings, rank filing types and passages, and synthesize answers from evidence using MCP tools, with MLflow tracing and FinAgentBench evaluation.

Serves project memory to AI agents, providing task-scoped context, tracked changes, validation evidence, and history to keep modifications grounded in current project facts.