feature_summary
Pack: uniprot · Endpoint: https://gateway.pipeworx.io/uniprot/mcp
“Domain map of [protein]” / “annotated features of [accession]” / “what regions / sites does [protein] have” — annotated features (domains, active sites, transmembrane regions, mutagenesis sites, glycosylation, disulfide bonds, etc.) for a UniProt accession. Use for structural/functional analysis without pulling the full protein record.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
accession | string | yes |
Example call
Arguments
{
"accession": "P38398"
}
curl
curl -X POST https://gateway.pipeworx.io/uniprot/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"feature_summary","arguments":{"accession":"P38398"}}}'
TypeScript (@pipeworx/sdk)
import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();
const result = await pipeworx.call('feature_summary', {
"accession": "P38398"
});
Response shape
Always returns: accession, total, by_type
| Field | Type | Description |
|---|---|---|
accession | string | UniProt accession |
total | number | Total number of annotated features |
by_type | object | Feature count by type |
Full JSON Schema
{
"type": "object",
"description": "Feature annotation summary for a protein",
"properties": {
"accession": {
"type": "string",
"description": "UniProt accession"
},
"total": {
"type": "number",
"description": "Total number of annotated features"
},
"by_type": {
"type": "object",
"description": "Feature count by type",
"additionalProperties": {
"type": "number",
"description": "Count for feature type"
}
}
},
"required": [
"accession",
"total",
"by_type"
]
}
Connect
Add this to your MCP client config, or use one-click install buttons:
{
"mcpServers": {
"uniprot": {
"url": "https://gateway.pipeworx.io/uniprot/mcp"
}
}
}
See Getting Started for client-specific install steps.