`trending_papers`

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

Today’s trending ML/AI papers (or a given day’s), ranked by community upvotes, via Hugging Face Papers. Use for “what are the hot AI papers”, “trending ML research”, “top papers this week”.

Parameters

Name	Type	Required	Description
`date`	string	no	Optional day YYYY-MM-DD (default: latest).
`limit`	number	no	Max papers to return (1-50, default 15).

Example call

Arguments

{
  "limit": 15
}

curl

curl -X POST https://gateway.pipeworx.io/paperswithcode/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"trending_papers","arguments":{"limit":15}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('trending_papers', {
  "limit": 15
});

Response shape

Field	Type	Description
`date`	string
`count`	number
`papers`	array	Array of formatted paper objects

Full JSON Schema

{
  "type": "object",
  "properties": {
    "date": {
      "type": "string"
    },
    "count": {
      "type": "number"
    },
    "papers": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "arxiv_id": {
            "type": "string",
            "description": "ArXiv ID of the paper"
          },
          "title": {
            "type": "string",
            "description": "Paper title"
          },
          "authors": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "List of paper authors"
          },
          "upvotes": {
            "type": "number"
          },
          "published": {
            "type": "string",
            "description": "Publication date"
          },
          "github_repo": {
            "type": [
              "string",
              "null"
            ]
          },
          "url": {
            "type": "string"
          }
        }
      },
      "description": "Array of formatted paper objects"
    }
  }
}

Connect

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

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

See Getting Started for client-specific install steps.

trending_papers