io.github.cyanheads/pharmacogenomics-guidelines-mcp-server

Retrieve guideline coverage by source ID, exact gene symbol or exact drug name/ID. Default summary pages complete guideline records with exact drugCount/pairCount. view=drugs or pairs requires by=id and pages only that related collection, retaining its guideline descriptor. Ambiguous drug names page candidates for retry with drugId. Follow page.nextOffset; the 24,000-byte soft budget cuts only between complete rows, with oversizedRow for an indivisible exception. Missing coverage is found=false. Consult linked guidelines before clinical use.

Browse CPIC recommendations in drug mode with one exact drugName or drugId. Match across drugs in results mode with geneResults or geneSymbol plus phenotype/activityScore, or genotype mode with 1–10 uniquely resolved gene/diplotype entries. Both matching modes accept an optional drug. Optional view=test_alerts selects complete example CDS alerts instead of recommendations, without joins; default view=recommendations. Alert records retain ordered alerttext, No CDS and n/a. Use pgx_list_reference topic phenotypes for source values. Every matched prerequisite must be explicit; omitted genes are never normal, negative or No Result. Preserve populations, scores, classifications and source text. Follow page.nextOffset and incompletePage.nextOffset independently for the selected collection and missing-gene diagnostics; consult source guidelines before clinical use.

Inspect gene symbols, gene-specific source results, CPIC levels, ClinPGx testing labels, recommendation classifications and input formats. phenotypes requires geneSymbol and preserves distinct activity-score rows, frequencies and consultation text. Live genes/phenotypes support paging; static topics return their complete vocabulary without upstream requests. Use returned values in subsequent discovery, diplotype and recommendation calls.

Translate a CPIC-supported diplotype or allele-status result for one gene. Supply geneSymbol and exact diplotype notation, including star alleles, named HLA positive/negative statuses, or non-star sequences; use pgx_search_alleles and pgx_list_reference with topic phenotypes to inspect supported values. Exact lookup precedes bounded reverse-order or status aliases. Multiple source rows remain ambiguous; no activity score or missing gene result is inferred.

Inspect CPIC allele function, evidence, definition metadata and complete population frequencies for geneSymbol. Name matches literally first, then a matching gene prefix before a star allele may be removed; clinicalFunctionalStatus matches literal text case-insensitively. Discover genes with pgx_list_reference. Definitions are metadata, not variant interpretation. Frequencies are source fractions; inferred frequencies are not observations and do not establish individual risk. Pages have a 24,000-byte complete-result soft budget; an indivisible exception sets oversizedRow. Continue with page.nextOffset.

Search evaluated gene–drug pairs by gene, literal drug-name substring, exact drug/RxNorm/ATC identifiers, evaluation level or testing label. Filters combine with AND; identifiers never fall back to name-only search. Results include source drug identifiers and guideline links for pgx_get_guideline. A pair evaluation is not a prescribing recommendation. Follow nextOffset to continue.