Enables any MCP client to run a complete data-science pipeline on a CSV: exploration, cleaning, model comparison, training, tuning, and plain-language analysis. Exposes nine tools that turn raw data into trained models and reports.
Enables LLM evaluation and observability by uploading documents, building test sets, running RAG pipelines, and automatically scoring answers for groundedness, hallucination risk, retrieval quality, latency, and cost, with tools exposed to MCP-compatible clients.
Provides MCP-compatible tools for data analysis, including file reading, Python/SQL execution, and hypothesis testing. Enables autonomous data analysis agents to interact with a sandboxed environment.