Gives Claude tools to screen biomedical literature and extract structured data from PubMed, GEO datasets, and preprints. It accepts mixed lists of PMIDs, DOIs, and GEO accessions, retrieves full text from PMC, Europe PMC, bioRxiv/medRxiv, Unpaywall, and Semantic Scholar, then runs LLM-based screening against custom criteria and extraction into CSV with configurable fields. Useful when you're triaging weekly PubMed alerts, building literature review tables, or pulling experimental metadata from GEO records. Supports batch processing through Anthropic and OpenAI batch APIs to cut per-request costs in half. Can generate prose markdown summaries alongside the CSV and stores all retrieved artifacts per record for audit.
claude mcp add --transport stdio rachadele-biolit uvx biolit