`get_recommendations`

Pack: tastedive · Endpoint: https://gateway.pipeworx.io/tastedive/mcp

Return ‘similar to X’ recommendations from TasteDive for a seed query (title or comma-separated titles). Optionally restrict to one media category (music/movie/show/book/game/podcast). Returns name, type, and optionally Wikipedia teaser + URL per recommendation.

Parameters

Name	Type	Required	Description
`query`	string	yes	Seed — one or more titles, comma-separated. Prefix with `<type>:` to disambiguate (e.g., “movie:Inception”).
`type`	string	no	Restrict to one category. Note: types are singular (movie, show, book), not plural.
`limit`	number	no	1-50 (default 20)
`include_info`	boolean	no	Add description + Wikipedia URL (default false)

Example call

Arguments

{
  "query": "Inception",
  "type": "movie",
  "limit": 10,
  "include_info": true
}

curl

curl -X POST https://gateway.pipeworx.io/tastedive/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_recommendations","arguments":{"query":"Inception","type":"movie","limit":10,"include_info":true}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('get_recommendations', {
  "query": "Inception",
  "type": "movie",
  "limit": 10,
  "include_info": true
});

More examples

{
  "query": "The Beatles, David Bowie",
  "type": "music"
}

Response shape

Always returns: query, type, seed_resolved, count, recommendations

Field	Type	Description
`query`	string	The seed query passed to TasteDive
`type`	string	The category filter applied (or ‘mixed’ if none specified)
`seed_resolved`	array	Resolved seed item(s) with name and type
`count`	number	Number of recommendations returned
`recommendations`	array	List of similar items from TasteDive

Full JSON Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "The seed query passed to TasteDive"
    },
    "type": {
      "type": "string",
      "description": "The category filter applied (or 'mixed' if none specified)"
    },
    "seed_resolved": {
      "type": "array",
      "description": "Resolved seed item(s) with name and type",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": [
              "string",
              "null"
            ],
            "description": "Name of the seed item"
          },
          "type": {
            "type": [
              "string",
              "null"
            ],
            "description": "Type/category of the seed item"
          }
        }
      }
    },
    "count": {
      "type": "number",
      "description": "Number of recommendations returned"
    },
    "recommendations": {
      "type": "array",
      "description": "List of similar items from TasteDive",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": [
              "string",
              "null"
            ],
            "description": "Name of the recommended item"
          },
          "type": {
            "type": [
              "string",
              "null"
            ],
            "description": "Type/category of the recommended item"
          },
          "teaser": {
            "type": [
              "string",
              "null"
            ],
            "description": "Short description from Wikipedia teaser"
          },
          "wikipedia": {
            "type": [
              "string",
              "null"
            ],
            "description": "Wikipedia URL for the item"
          },
          "youtube": {
            "type": [
              "string",
              "null"
            ],
            "description": "YouTube URL for the item"
          }
        }
      }
    }
  },
  "required": [
    "query",
    "type",
    "seed_resolved",
    "count",
    "recommendations"
  ]
}

Connect

Add this to your MCP client config, or use one-click install buttons:

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

See Getting Started for client-specific install steps.

get_recommendations