`mgnify_biomes`

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

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

List MGnify’s controlled biome vocabulary — the ~492 colon-delimited lineages (root:Host-associated:Human:Digestive system:Large intestine:Fecal, root:Environmental:Aquatic:Marine…) that every MGnify study is classified under. This is the lookup step before filtering studies or genomes by environment: the lineage strings are exact and are not guessable. Optionally narrow to one subtree by prefix.

Parameters

Name	Type	Required	Description
`lineage_prefix`	string	no	Keep only lineages starting with this, e.g. “root:Host-associated:Human” or “root:Environmental”.
`limit`	number	no	Maximum lineages to return, 1-200 (default 20).

Example call

Arguments

{
  "lineage_prefix": "root:Host-associated:Human",
  "limit": 5
}

curl

curl -X POST https://gateway.pipeworx.io/mgnify/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"mgnify_biomes","arguments":{"lineage_prefix":"root:Host-associated:Human","limit":5}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('mgnify_biomes', {
  "lineage_prefix": "root:Host-associated:Human",
  "limit": 5
});

More examples

{
  "limit": 20
}

Connect

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

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

See Getting Started for client-specific install steps.

mgnify_biomes