esearch
Pack: ncbi-eutils · Endpoint: https://gateway.pipeworx.io/ncbi-eutils/mcp
Search an Entrez database (e.g. pubmed, gene, nucleotide) by query term and return a list of matching UIDs (up to 10,000) with hit count. Supports pagination via retstart and sort (e.g. pub_date).
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
db | string | yes | |
term | string | yes | |
retmax | number | no | 1-10000 (default 20) |
retstart | number | no | |
sort | string | no | e.g. “pub_date” (PubMed), “relevance” |
Example call
Arguments
{
"db": "pubmed",
"term": "BRCA1 mutations"
}
curl
curl -X POST https://gateway.pipeworx.io/ncbi-eutils/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"esearch","arguments":{"db":"pubmed","term":"BRCA1 mutations"}}}'
TypeScript (@pipeworx/sdk)
import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();
const result = await pipeworx.call('esearch', {
"db": "pubmed",
"term": "BRCA1 mutations"
});
More examples
{
"db": "nucleotide",
"term": "human insulin",
"retmax": 100,
"sort": "pub_date"
}
Response shape
Full JSON Schema
{
"type": "object",
"description": "NCBI esearch response - search results with UIDs"
}
Connect
Add this to your MCP client config, or use one-click install buttons:
{
"mcpServers": {
"ncbi-eutils": {
"url": "https://gateway.pipeworx.io/ncbi-eutils/mcp"
}
}
}
See Getting Started for client-specific install steps.