For AI agents

DataClue MCP server

Let your AI assistant search our catalog, compare specs and pricing, and request samples or a quote for you. Public, no API key needed.

Endpoint

https://dataclue.app/mcp

Streamable HTTP transport, no authentication. Discovery card: /.well-known/mcp.json.

Connect

  • Claude (claude.ai or Claude Desktop): Settings → Connectors → Add custom connector, and paste the endpoint URL.
  • Claude Code: claude mcp add --transport http dataclue https://dataclue.app/mcp
  • ChatGPT (developer mode), Cursor, VS Code and other MCP clients: add a remote MCP server with the endpoint URL, or use this config:
{
  "mcpServers": {
    "dataclue": {
      "type": "http",
      "url": "https://dataclue.app/mcp"
    }
  }
}

Tools

  • search_datasets — Search DataClue's catalog of licensable AI training data (egocentric video of real work, UMI gripper demonstrations) with a plain-English need, e.g. "50,000 hours of household manipulation video, 1080p, long sessions". Returns matching datasets with hours in stock, price per hour, scenarios and which requirements they meet, plus custom-collection options when nothing in stock fits.
  • get_dataset — Full details for one DataClue dataset: overview, scenarios with measured sample specs, delivered resolution, sensors, annotation, delivery format, licensing, FAQs, sample clip URLs and price.
  • get_pricing_and_terms — DataClue's list prices, what is included, quote paths (free samples, paid pilot, volume quote, custom collection), licensing, payment and consent terms.
  • request_quote — Send a request to DataClue's sales team on the user's behalf: free evaluation samples, a paid pilot, a volume quote, or a custom collection. Side effect: emails the request (including the user's name, work email and company) to DataClue, who reply to that email. Only call this when the user has asked to contact DataClue and has provided their own work email, and show them the details to confirm before sending. Each call sends a new request, so do not retry a successful call.

Try it

curl -s https://dataclue.app/mcp \
  -H 'content-type: application/json' \
  -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_datasets","arguments":{"query":"household manipulation video, 1080p"}}}'

Prefer a person? contact@dataclue.app · Request a quote · llms.txt