`search`

Pack: harvard-art · 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 Harvard Art Museums collection by keyword. Returns matching items with ids (pass an id to object), titles, creators, dates and image links.

Parameters

Name	Type	Required	Description
`query`	string	yes	Keyword(s), e.g. “rembrandt”, “ceramics”, “moon landing”.
`limit`	number	no	Max results (1-100, default 20).
`page`	number	no	Page number (1-based, default 1).
`_apiKey`	string	no	Harvard Art Museums API key (auto-injected by the platform; or pass your own).

Example call

Arguments

{
  "query": "rembrandt",
  "_apiKey": "your-harvard-art-api-key"
}

curl

curl -X POST https://gateway.pipeworx.io/harvard-art/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search","arguments":{"query":"rembrandt","_apiKey":"your-harvard-art-api-key"}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('search', {
  "query": "rembrandt",
  "_apiKey": "your-harvard-art-api-key"
});

More examples

{
  "query": "ceramics",
  "limit": 50,
  "page": 1,
  "_apiKey": "your-harvard-art-api-key"
}

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 harvard-art pack

{
  "mcpServers": {
    "harvard-art": {
      "url": "https://gateway.pipeworx.io/harvard-art/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

search