Integration

Auckland Museum API integration

The Auckland War Memorial Museum (Tamaki Paenga Hira) publishes its collections as Linked Open Data: natural science specimens, human history objects, documentary heritage (photographs, paintings, manuscripts), people and the Online Cenotaph of New Zealand service people. Find subjects with SPARQL queries, read every predicate of one subject (titles, dates, materials, places, people, images) by its identifier, and download its images or PDF documents in several renderings. The Elasticsearch search route is not exposed: it answers a browser JavaScript challenge to API clients. No credential is needed; the museum limits SPARQL to 5 requests per second and 100 per day and other routes to 10 per second and 1000 per day.

Connect Auckland Museum API How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Auckland Museum API.Built from the 3 Auckland Museum API tools below, on the connection you add once.

What you can do with Auckland Museum API

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Id, 1 operation

get_subjectGet subjectGETReturns every predicate of one collection subject (an object, specimen, image, person, place, Cenotaph record...) as JSON: titles, dates, materials, people, places, notes and links to its images and related subjects.

Media, 1 operation

download_mediaDownload mediaGETDownloads an image or PDF document of a collection subject as a file, in the original size or a smaller rendering (thumbnail 70 px wide, preview 100 px high, standard 440 by 440 px).

Sparql, 1 operation

run_sparql_queryRun sparql queryPOSTRuns a SPARQL SELECT query over the whole collection graph (10 second limit, 100 queries a day) and returns the variable names and one binding per result row.

Use Auckland Museum API from Claude Code, Cursor or Codex

Connect Auckland Museum API in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Auckland Museum API operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Auckland Museum API

Create your workspace
Sign up free. Nothing to install.
Connect Auckland Museum API once
Auckland Museum API needs no credential, so its tools work immediately.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.