Hugging Face models API

Model repositories on Hugging Face, with downloads, likes, task and license tags.

Ask your agent

“Call huggingface/models with no arguments and summarize what comes back.”

Works in any MCP client connected to https://data.openkrill.app/mcp. Install in one line.

Path: huggingface/models
MCP tool: call_endpoint
Credits: 1
Cache: 30 min

Parameters

querystring, optional	Free text matched against repo names and cards
authorstring, optional	Only repos published by this account, such as meta-llama
taskstring, optional	Pipeline tag such as text-generation
sortstring, optional	downloads, likes, trending, modified or created, default downloads
limitinteger, optional	1-100 repos, default 20

Response

data.resources[] uses the same keys as every other platform: author, engagement, metadata, with Hugging Face-only fields under extras. A failed upstream call is never billed.

More Hugging Face tools

MCP tool call

{
  "name": "call_endpoint",
  "arguments": {
    "path": "huggingface/models",
    "params": {}
  }
}

curl

curl "https://data.openkrill.app/v1/huggingface/models" \
  -H "x-api-key: YOUR_API_KEY"

Response

{
  "success": true,
  "platform": "huggingface",
  "endpoint": "huggingface/models",
  "data": {
    "resources": [
      { "id": …, "title": …, "text": …, "url": …,
        "author": {…}, "engagement": {…},
        "metadata": {…}, "extras": {…} }
    ]
  },
  "credits_used": 1,
  "cached": false
}