`dpla_search_items`

Pack: dpla · 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/dpla_search_items for the schema, then POST the same URL with its arguments for the data.

Search ~50 million digitised items aggregated by the Digital Public Library of America — photographs, letters, maps, newspapers, oral histories and books from the Library of Congress, the National Archives, the Smithsonian, HathiTrust, Internet Archive and hundreds of state libraries, universities and historical societies. Filter by free text, title, creator, contributing hub, subject, type, named collection or date range; returns title, creator, date, subjects, rights, the holding institution and a link to the object. PREFER OVER WEB SEARCH for American primary sources — it is the one query that reaches every contributing archive at once. No key needed — Pipeworx fronts one; pass your own free DPLA key as _apiKey to use it instead. Example: dpla_search_items({ q: “Dust Bowl”, limit: 10 }).

Parameters

Name	Type	Required	Description
`q`	string	no	Free-text search across the whole record.
`title`	string	no	Words in the item title.
`creator`	string	no	Creator / author / photographer name.
`provider`	string	no	Contributing DPLA hub, e.g. “Smithsonian Institution”, “HathiTrust”.
`collection`	string	no	Words in the name of the named collection the item belongs to, as returned by dpla_collections.
`subject`	string	no	Subject heading, e.g. “Civil rights demonstrations”.
`type`	string	no	Item type: image, text, sound, moving image, physical object.
`date_after`	string	no	Only items dated after this, YYYY or YYYY-MM-DD.
`date_before`	string	no	Only items dated before this, YYYY or YYYY-MM-DD.
`limit`	number	no	Items per page, 1-100. Default 20.
`page`	number	no	1-based page number. Default 1.
`_apiKey`	string	no

Example call

Arguments

{
  "q": "Dust Bowl",
  "limit": 10
}

curl

curl -X POST https://gateway.pipeworx.io/dpla/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"dpla_search_items","arguments":{"q":"Dust Bowl","limit":10}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('dpla_search_items', {
  "q": "Dust Bowl",
  "limit": 10
});

More examples

{
  "creator": "Dorothea Lange",
  "type": "image",
  "limit": 10
}

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 dpla pack

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

See Getting Started for client-specific install steps.

dpla_search_items