@pipeworx/herb-tcm

HERB 2.0's Traditional Chinese Medicine knowledge base — herbs, ingredients, gene targets, diseases, PubMed-cited papers and GEO transcriptomic experiments — proxied live from herb.ac.cn, with every relationship row tagged an evidence_tier so a statistical prediction is never mistaken for proof of efficacy.

Part of Pipeworx — an MCP gateway connecting AI agents to 1865+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• herb_search(keyword, category?) — resolve a name to an id. Accepts Chinese characters, pinyin, English/Latin names, gene names/aliases, disease names, or a HERB id itself. category is one of herb / ingredient / target / disease (default herb).
• herb_browse(category, page?, page_size?) — page through the full herb/ingredient/target/disease list (7,263 / 49,258 / 12,933 / 28,212 rows respectively).
• herb_detail(id, category, limit?, offset?, sections?) — the full record for one id: composition, traditional-use summary, and every predicted or literature-backed target/disease relationship, each carrying its evidence_tier. Relationship tables are paged (fleet #1399 — an unpaged well-studied herb ran to 806 KB): each comes back as {total, offset, limit, returned, truncated, rows} where total is the TRUE upstream row count and truncated: true says more rows exist — so a 25-row slice can never be mistaken for 25 rows existing. limit defaults to 25 (the pack's precedent, set by herb_papers), max 200; offset pages; sections (e.g. ["summary","herb_ingredient"]) fetches composition without pulling thousands of predicted disease rows, and an unknown section name errors loudly rather than silently returning nothing. We chose client-side slicing over a sections-only design because detail_api has no server-side paging (one upstream call returns everything regardless), so the slice costs nothing extra and the envelope keeps the caller honest. ingredient_alias (a small synonym list) is never paged.
• herb_papers(drug_type?, experiment_type?, sort_by?, limit?, offset?) — list PubMed-cited references, each tagged human_clinical or laboratory.
• herb_paper_detail(paper_id) — one reference's bibliographic record plus the specific targets/diseases it reports.
• herb_experiments(drug_type?, species?, experiment_type?, limit?, offset?) — list GEO-deposited herb/ingredient-vs-control transcriptomic experiments.
• herb_experiment_detail(experiment_id) — differential-expression results for one experiment: top up/down genes, enriched GO/KEGG terms, connectivity-map hit counts. Always evidence_tier: computational_prediction.

Evidence tiers

Every relationship row carries one of:

herb_target / herb_disease (statistical enrichment, p-value + FDR_BH columns), ingredient_target / ingredient_disease / target_disease (curated cross-references with no clinical backing) and every herb_experiment_detail row are computational_prediction. drug_paper_target / drug_paper_disease (PubMed-cited) are split into human_clinical or laboratory by resolving each cited paper's own "Experiment type" — s

... View full README on GitHub