Search Hugging Face papers
hugging_face_papers_searchSearch Hugging Face papers by keyword or list the newest publications; use cursor pagination to browse result pages.
Instructions
Search Hugging Face papers by keyword, or list the newest papers. Optional inputs: query, limit and cursor. Returns a list (use cursor when paginated).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "hugging_face_papers_search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Items per page, 1-100. A page can hold fewer. Default: 50. | |
| query | No | Search text. Without it the endpoint lists the newest papers. A search returns up to 120 papers and has no further pages. | |
| cursor | No | Pass `page.nextCursor` from the previous response to get the next page. Keep every other parameter the same. | |
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| llm_model | Yes | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess. | |
| conversation_id | No | Echo the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it. |