`search`

Pack: nypl · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)

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

Search the NYPL Digital Collections collection by keyword. Returns matching items with ids (pass an id to item), titles, creators/sources, dates and links.

Parameters

Name	Type	Required	Description
`query`	string	yes	Keyword(s).
`limit`	number	no	Max results (1-100, default 20).
`page`	number	no	Page (1-based, default 1).
`_apiKey`	string	no	NYPL Digital Collections API key (auto-injected by the platform).

Example call

Arguments

{
  "query": "Civil War photographs"
}

curl

curl -X POST https://gateway.pipeworx.io/nypl/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search","arguments":{"query":"Civil War photographs"}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('search', {
  "query": "Civil War photographs"
});

More examples

{
  "query": "New York maps 1850",
  "limit": 50,
  "page": 1
}

Connect

Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:

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

Connect to just the nypl pack

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

See Getting Started for client-specific install steps.

search