`biomodels_search`

Pack: biomodels · Endpoint: https://gateway.pipeworx.io/biomodels/mcp

No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/biomodels_search for the schema, then POST the same URL with its arguments for the data.

Search BioModels for published, executable mathematical models of biological systems — metabolic pathways, signalling cascades, cell-cycle and circadian oscillators, whole-cell metabolic reconstructions, infectious-disease models. AUTHORITATIVE for “is there a published computational model of X I can actually run”, which web search answers with papers rather than with loadable SBML. Returns model id, name, format, submitter and date, plus facet counts (curation status, modelling approach, and cross-referenced taxonomy/GO/UniProt/ChEBI terms) that show how the matching models break down. Search accepts pathway names, diseases, organisms, genes, proteins and author names.

Parameters

Name	Type	Required	Description
`query`	string	yes	Free-text query: a pathway (“glycolysis”), process (“circadian”), disease, organism, gene/protein, or author surname.
`limit`	number	no	Maximum models to return, 1-100 (default 10).
`offset`	number	no	Row offset for paging; add the previous limit to page forward.

Example call

Arguments

{
  "query": "glycolysis",
  "limit": 3
}

curl

curl -X POST https://gateway.pipeworx.io/biomodels/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"biomodels_search","arguments":{"query":"glycolysis","limit":3}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('biomodels_search', {
  "query": "glycolysis",
  "limit": 3
});

More examples

{
  "query": "circadian",
  "limit": 10,
  "offset": 10
}

Connect

Add this to your MCP client config, or use one-click install buttons:

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

See Getting Started for client-specific install steps.

biomodels_search