MCP gateway federating 21 biomedical MCP servers — gnomAD, ClinVar, HPO, UniProt, Ensembl VEP, PanelApp and more — behind one Streamable-HTTP endpoint, with collision-free namespaced tools and BM25 tool search.

MCP server for STRING v12: protein–protein association networks, interaction partners, and functional enrichment analysis — as typed tools for LLM agents.

MCP server for MGI (Mouse Genome Informatics): mouse gene, allele, mutation and phenotype data — the MGI marker page as structured tools, served from a local SQLite index.

MCP server for HGNC (HUGO Gene Nomenclature Committee, genenames.org): gene symbol and ID resolution, cross-references, search, and gene groups — served from a local index of the HGNC bulk download.

MCP server for NCBI PubTator3: biomedical literature search with gene, variant, disease and chemical entity annotation — returns compact, citable passages instead of raw BioC.

MCP server for PanelApp: consensus diagnostic gene panels and gene–disease ratings from Genomics England (UK) and PanelApp Australia — as typed tools for LLM agents.

MCP server for the Mondo Disease Ontology: disease term lookup, the is_a hierarchy, and cross-ontology mapping across OMIM, Orphanet, DOID, NCIT, UMLS and MeSH.

MCP server for MaveDB: quantitative variant-effect scores from Multiplexed Assays of Variant Effect (MAVE) and deep mutational scanning — functional evidence as typed tools for LLM agents.

MCP server for the GTEx Portal: tissue-specific gene expression — median and per-sample TPM, top expressed genes per tissue, and gene/transcript annotation — as typed tools for LLM agents.

MCP server for NCBI ClinVar: variant clinical significance and gene-level classifications, served from a local SQLite index built from the ClinVar weekly bulk release — not the eUtils API.

MCP server for Ensembl VEP (Variant Effect Predictor) and Variant Recoder: variant consequence annotation and identifier recoding across GRCh38 and GRCh37.

MCP server for UniProt: protein function, sequence, features and cross-references over the UniProt SPARQL endpoint — intent-named tools plus a guarded raw-SPARQL escape hatch.

MCP server for GeneReviews: the expert-authored, peer-reviewed gene–disease chapters on NCBI Bookshelf, served as a searchable corpus of individually citable passages.

MCP server for SpliceAI Lookup (Broad Institute): SpliceAI, Pangolin and SpliceAI-10k splice-impact predictions for variants, plus an Ensembl VEP-backed variant resolver.

MCP server for GenCC (Gene Curation Coalition): harmonized gene–disease validity classifications across member submitters, with consensus and conflict detection per gene–disease pair.

MCP server for ClinGen (Clinical Genome Resource): gene–disease validity, dosage sensitivity, clinical actionability, and expert-panel variant pathogenicity (ERepo) — as typed tools for LLM agents.

MCP server for NCBI LitVar2: search the biomedical literature by genetic variant — the index linking variants to the publications that mention them, as typed tools for LLM agents.

MCP server for MetaDome: per-position missense tolerance (dN/dS) landscapes for human transcripts, Pfam domains, meta-domain homolog aggregation, and gnomAD/ClinVar per-position counts.

MCP server for AutoPVS1: automated ACMG PVS1 loss-of-function evidence for sequence variants and copy-number variants — variant interpretation as typed tools for LLM agents.

MCP server for Orphanet (Orphadata): rare-disease nomenclature, gene–disease associations, phenotypes, epidemiology and cross-references, from the Orphadata scientific knowledge files.