Bioportal MCP server

@pipeworx/bioportal

Term search, class lookup and cross-ontology mappings over the ~1,300 biomedical ontologies NCBO's BioPortal carries — NCIT, SNOMEDCT, LOINC, RXNORM, MESH, HPO, ICD10CM, GO and the rest.

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Tools

— free text to coded concept, with preferred label, synonyms, definition, CUI and the permanent class IRI.

• bioportalsearch(query, ontologies?, exactmatch?, require_definitions?, limit?)

can find the acronym before you search.

• bioportal_ontologies(filter?, limit?) — the catalogue of ontologies, so you

equivalent concept in other ontologies, with the mapping method.

• bioportalclass(ontology, classid) — the full record for one class.
• bioportalmappings(ontology, classid, to_ontology?, limit?) — the

Auth

BioPortal requires an apikey on every request. Resolution order in this pack:

shared across all of its users and rate-limited accordingly.

1. caller-supplied _apiKey (free key, https://bioportal.bioontology.org/accounts/new),
2. otherwise the demo key NCBO publishes in its own REST documentation, which is

Every response carries key_source so a caller can see which one answered.

When a platform key is provisioned (PLATFORMBIOPORTALKEY), the change is one line: add "platformKeyEnv": "PLATFORMBIOPORTALKEY" to this pack's entry in workers/gateway/src/pack-manifest.json and re-run node scripts/sync-pack-manifest.mjs. The gateway then injects it as _apiKey and the demo fallback stops being reached. It is deliberately NOT declared today: keyBlockedTools() in the gateway marks every tool of a pack that declares an UNSET platformKeyEnv as key-blocked, which would sink a pack that currently works for everyone.

Data sources

require_definitions, pagesize.

• — q, ontologies, exact_match,

and its /mappings child.

• — the catalogue.

Things that will otherwise cost you an afternoon:

/ontologies. Use it there.

• displaylinks=false is the difference between 4.4 MB and 312 KB** on

derivable from links.ontology. Its @id is a purl (http://purl.bioontology.org/ontology/MESH/D008545) whose path segment is not reliably the acronym.

• But do NOT set it on /search: a search hit's ontology acronym is only

included — e.g. /ontologies/NCIT/classes/http%3A%2F%2Fncicb.nci.nih.gov%2Fxml%2Fowl%2FEVS%2FThesaurus.owl%23C3224.

• The class IRI must be URL-encoded as a single path segment — # and /

asked about. Pick the one whose ontology is not the source, or every mapping looks like a self-mapping.

• A mapping record lists BOTH ends in classes, including the class you

has 114 mappings and none of them are to SNOMEDCT — the targets are CADSR-VS, RH-MESH, MESH, MEDDRA, LOINC and a long tail. An empty to_ontology filter result is a real answer, not a failure.

• Not every concept maps to the big terminologies. NCIT "Melanoma" (C3224)

Scope, so nobody builds this twice

The ols pack covers EBI's Ontology Lookup Service — a different repository with a different, OBO-leaning set of ontologies. BioPortal is the one carrying the US clinical terminologies. cbioportal is cancer genomics and is unrelated despite the name.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "bioportal": {
      "url": "https://gateway.pipeworx.io/bioportal/mcp"
    }
  }
}

What this endpoint actually serves

Shortened. The full README is on GitHub.