Huggingface Daily Papers

Instructions

Implementation Reference

• scraper.py:19-39 (handler)

  Core implementation of the get_papers_by_date tool. Fetches papers from HuggingFace for the given date, parses the HTML, and optionally fetches additional details like abstracts and authors from individual paper pages and ArXiv.

  def get_papers_by_date(self, date: str, fetch_details: bool = True) -> List[Dict]:
      url = f"{self.base_url}/{date}"
      try:
          response = self.session.get(url)
          response.raise_for_status()
          papers = self._parse_papers(response.text)
          
          if fetch_details and papers:
              # 获取所有论文的详细信息，包括具体作者姓名
              for i, paper in enumerate(papers):
                  if paper.get('url'):
                      details = self._fetch_paper_details(paper['url'])
                      if details:
                          paper.update(details)
                      time.sleep(1)  # 避免请求过快
                      
          return papers
      except requests.RequestException as e:
          logging.error(f"Failed to fetch papers for {date}: {e}")
          return []

• main.py:60-74 (registration)

  MCP tool registration defining the tool name, description, and input schema (date parameter with YYYY-MM-DD pattern).

  types.Tool(
      name="get_papers_by_date",
      description="Get HuggingFace daily papers for a specific date",
      inputSchema={
          "type": "object",
          "properties": {
              "date": {
                  "type": "string",
                  "description": "Date in YYYY-MM-DD format",
                  "pattern": r"^\d{4}-\d{2}-\d{2}$"
              }
          },
          "required": ["date"]
      },
  ),

• main.py:63-73 (schema)

  Input schema definition for the get_papers_by_date tool, specifying the required 'date' parameter.

  inputSchema={
      "type": "object",
      "properties": {
          "date": {
              "type": "string",
              "description": "Date in YYYY-MM-DD format",
              "pattern": r"^\d{4}-\d{2}-\d{2}$"
          }
      },
      "required": ["date"]
  },

• main.py:100-132 (handler)

  MCP server @server.call_tool() dispatch logic for get_papers_by_date: validates input, calls scraper.get_papers_by_date, handles empty results, and formats the output as formatted text content.

  if name == "get_papers_by_date":
      if not arguments or "date" not in arguments:
          raise ValueError("Date is required")
      
      date = arguments["date"]
      papers = scraper.get_papers_by_date(date)
      
      if not papers:
          return [
              types.TextContent(
                  type="text",
                  text=f"No papers found for {date}. Please check if the date is correct and has published papers."
              )
          ]
      
      return [
          types.TextContent(
              type="text",
              text=f"Found {len(papers)} papers for {date}:\n\n" + 
                   "\n".join([
                       f"Title: {paper['title']}\n"
                       f"Authors: {', '.join(paper['authors'])}\n" 
                       f"Abstract: {paper['abstract']}\n"
                       f"URL: {paper['url']}\n"
                       f"PDF: {paper['pdf_url']}\n"
                       f"Votes: {paper['votes']}\n"
                       f"Submitted by: {paper['submitted_by']}\n"
                       + "-" * 50
                       for paper in papers
                   ])
          )
      ]