Hugging Face papers API

Papers Hugging Face indexes, with authors, abstract, upvotes and the model-written summary.

Ask your agent

“Call huggingface/papers with query open source and summarize what comes back.”

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

Path: huggingface/papers
MCP tool: call_endpoint
Credits: 1
Cache: 2 min

Parameters

querystring, required	Search text matched against titles and abstracts
limitinteger, optional	1-100, default 10

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/papers",
    "params": {
      "query": "open source"
    }
  }
}

curl

curl "https://data.openkrill.app/v1/huggingface/papers?query=open+source" \
  -H "x-api-key: YOUR_API_KEY"

Response

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