`search_models`

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

Search Hugging Face Hub models with filters for author, library (transformers/diffusers/…), language, pipeline_tag (text-generation/…), and tags; sort by downloads, likes, or trending_score.

Parameters

Name	Type	Required	Description
`search`	string	no	Free-text — name / description
`author`	string	no	Filter by org or user (e.g. “meta-llama”)
`library`	string	no	transformers \| diffusers \| sentence-transformers \| …
`language`	string	no	ISO language code
`pipeline_tag`	string	no	text-generation \| text-classification \| image-classification \| translation \| …
`tags`	string	no	Comma-separated tags
`sort`	string	no	downloads \| likes \| trending_score \| lastModified \| createdAt
`direction`	string	no	-1 (desc, default) \| 1 (asc)
`limit`	number	no	1-1000 (default 20)
`full`	boolean	no	Include extra fields (cardData, gated, etc.)

Example call

Arguments

{
  "search": "bert",
  "library": "transformers",
  "limit": 20
}

curl

curl -X POST https://gateway.pipeworx.io/huggingface/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_models","arguments":{"search":"bert","library":"transformers","limit":20}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('search_models', {
  "search": "bert",
  "library": "transformers",
  "limit": 20
});

More examples

{
  "author": "meta-llama",
  "pipeline_tag": "text-generation",
  "sort": "downloads",
  "direction": "-1",
  "limit": 10
}

Response shape

Full JSON Schema

{
  "type": "object",
  "description": "List of models matching search criteria"
}

Connect

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

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

See Getting Started for client-specific install steps.

search_models