`datasets`

Pack: data-usdot · 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/datasets for the schema, then POST the same URL with its arguments for the data.

Search the US DOT Open Data catalog of open datasets by keyword. Returns each dataset’s resource_id, name, description, category and update date — pass the resource_id to query/metadata.

Parameters

Name	Type	Required	Description
`query`	string	no	Keyword to search dataset titles/descriptions (e.g. “budget”, “crime”, “health”).
`limit`	number	no	Max datasets (1-100, default 20).
`offset`	number	no	Pagination offset.

Example call

Arguments

{
  "query": "traffic accidents"
}

curl

curl -X POST https://gateway.pipeworx.io/data-usdot/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"datasets","arguments":{"query":"traffic accidents"}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('datasets', {
  "query": "traffic accidents"
});

More examples

{
  "query": "highway safety",
  "limit": 10,
  "offset": 0
}

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 data-usdot pack

{
  "mcpServers": {
    "data-usdot": {
      "url": "https://gateway.pipeworx.io/data-usdot/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

datasets