Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:386-400 (handler)

  The search_biorxiv handler function in server.py calls the async_search helper with the biorxiv_searcher platform instance.

  async def search_biorxiv(query: str, max_results: int = 10) -> List[Dict]:
      """Search academic papers from bioRxiv.
  
      Note: bioRxiv API filters by category name within the last 30 days, not full-text
      keyword search. Use a category keyword such as 'bioinformatics', 'neuroscience',
      'cell biology', etc.
  
      Args:
          query: Category name to filter by (e.g., 'bioinformatics', 'neuroscience').
          max_results: Maximum number of papers to return (default: 10).
      Returns:
          List of paper metadata in dictionary format.
      """
      papers = await async_search(biorxiv_searcher, query, max_results)
      return papers if papers else []

• paper_search_mcp/academic_platforms/biorxiv.py:19-84 (handler)

  The actual implementation of the search logic for bioRxiv, located in the BioRxivSearcher class.

  def search(self, query: str, max_results: int = 10, days: int = 30) -> List[Paper]:
      """
      Search for papers on bioRxiv by category within the last N days.
  
      Args:
          query: Category name to search for (e.g., "cell biology").
          max_results: Maximum number of papers to return.
          days: Number of days to look back for papers.
  
      Returns:
          List of Paper objects matching the category within the specified date range.
      """
      # Calculate date range: last N days
      end_date = datetime.now().strftime('%Y-%m-%d')
      start_date = (datetime.now() - timedelta(days=days)).strftime('%Y-%m-%d')
      
      # Format category: lowercase and replace spaces with underscores
      category = query.lower().replace(' ', '_')
      
      papers = []
      cursor = 0
      while len(papers) < max_results:
          url = f"{self.BASE_URL}/{start_date}/{end_date}/{cursor}"
          if category:
              url += f"?category={category}"
          tries = 0
          while tries < self.max_retries:
              try:
                  response = self.session.get(url, timeout=self.timeout)
                  response.raise_for_status()
                  data = response.json()
                  collection = data.get('collection', [])
                  for item in collection:
                      try:
                          date = datetime.strptime(item['date'], '%Y-%m-%d')
                          papers.append(Paper(
                              paper_id=item['doi'],
                              title=item['title'],
                              authors=item['authors'].split('; '),
                              abstract=item['abstract'],
                              url=f"https://www.biorxiv.org/content/{item['doi']}v{item.get('version', '1')}",
                              pdf_url=f"https://www.biorxiv.org/content/{item['doi']}v{item.get('version', '1')}.full.pdf",
                              published_date=date,
                              updated_date=date,
                              source="biorxiv",
                              categories=[item['category']],
                              keywords=[],
                              doi=item['doi']
                          ))
                      except Exception as e:
                          print(f"Error parsing bioRxiv entry: {e}")
                  if len(collection) < 100:
                      break  # No more results
                  cursor += 100
                  break  # Exit retry loop on success
              except requests.exceptions.RequestException as e:
                  tries += 1
                  if tries == self.max_retries:
                      print(f"Failed to connect to bioRxiv API after {self.max_retries} attempts: {e}")
                      break
                  print(f"Attempt {tries} failed, retrying...")
          else:
              continue
          break
  
      return papers[:max_results]