@pipeworx/ncbi-datasets

Connect: https://gateway.pipeworx.io/ncbi-datasets/mcp · Install: one-click buttons

No MCP client? Skip the connection: POST https://gateway.pipeworx.io/v1/tools/search_packs {"query":"..."} to find a tool below, GET /v1/tools/<name> for its schema, POST the same URL with arguments for the data — see For AI agents.

Tools: 3

NCBI Datasets (US National Library of Medicine) — which genome assemblies exist for an organism and how good they are, where a gene sits and what it is called in every other database, and the NCBI taxonomy tree with per-node assembly and gene counts.

Tools

• ncbi_genome_reports(taxon?, accession?, reference_only?, assembly_level?, limit?) — assemblies with level, length, contig/scaffold N50, GC%, submitter, BioProject and the paired RefSeq/GenBank accession.
• ncbi_gene_by_symbol(symbols, taxon?) — Entrez gene id, biotype, chromosome, RefSeqGene coordinates, plus HGNC / Ensembl / UniProt / OMIM cross-references and every synonym.
• ncbi_taxonomy(taxons) — resolve a tax id, scientific name or common name to the full lineage, children, rank and live assembly/gene counts.

Auth

Keyless. NCBI rate-limits anonymous callers by IP at roughly 5 requests/second across api.ncbi.nlm.nih.gov; the pack sends an identifying User-Agent, does not retry, and surfaces a 429 with that explanation rather than looping.

Not the same service as ncbi-eutils

E-utilities is a generic search/fetch layer over ~40 Entrez databases that hands back records you must parse. Datasets answers structured questions about genomes, genes and taxonomy with structured rows. Use this pack for those three; use ncbi-eutils for PubMed, dbSNP and the rest of Entrez.

Data sources

• https://api.ncbi.nlm.nih.gov/datasets/v2/genome/taxon/{taxon}/dataset_report
• https://api.ncbi.nlm.nih.gov/datasets/v2/genome/accession/{acc}/dataset_report
• https://api.ncbi.nlm.nih.gov/datasets/v2/gene/symbol/{symbols}/taxon/{taxon}
• https://api.ncbi.nlm.nih.gov/datasets/v2/taxonomy/taxon/{taxons}

Things that cost time to rediscover (measured 2026-09-17)

• Without filters, a genome report is every assembly ever deposited. Taxon 562 (E. coli) has 492,559, and page one of two is a GenBank/RefSeq pair of the same assembly — technically correct, practically useless. filters.reference_only=true takes that to 2, so ncbi_genome_reports defaults to it for a taxon lookup and reports that it did.
• Every assembly exists twice, as GCA_ (GenBank) and GCF_ (RefSeq), cross-linked by paired_accession. Counting rows double-counts assemblies.
• Multi-value paths do not preserve order. taxonomy/taxon/9606,10090 returns Mus musculus first. Match on the returned query / symbol, never on position.
• Numeric fields are strings in gene reports ("gene_id":"672") but numbers in taxonomy reports (tax_id: 9606). Both are passed through as received.
• A taxon path accepts a tax id, a scientific name or a common name — 9606, Homo sapiens and human all work.

Tools

• ncbi_genome_reports — List the genome assemblies NCBI holds for an organism (or fetch one by accession), with assembly level, total length, contig and scaffold N50, GC percent, submitter, release date, BioProject, and the
• ncbi_gene_by_symbol — Look up one or more genes by symbol in a given organism and get NCBI’s authoritative record: Entrez gene id, official description, biotype, chromosome and orientation, RefSeqGene coordinates, and the
• ncbi_taxonomy — Resolve organisms in the NCBI Taxonomy — the naming authority GenBank, ENA and DDBJ all classify against — from a tax id, scientific name or common name, returning the full ancestor lineage as tax ids