Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:358-368 (handler)

  The MCP tool wrapper that calls the async_search helper with the arxiv_searcher instance.

  async def search_arxiv(query: str, max_results: int = 10) -> List[Dict]:
      """Search academic papers from arXiv.
  
      Args:
          query: Search query string (e.g., 'machine learning').
          max_results: Maximum number of papers to return (default: 10).
      Returns:
          List of paper metadata in dictionary format.
      """
      papers = await async_search(arxiv_searcher, query, max_results)
      return papers if papers else []

• paper_search_mcp/academic_platforms/arxiv.py:24-79 (handler)

  The core implementation of the Arxiv search logic using feedparser to parse arXiv API response.

  def search(self, query: str, max_results: int = 10) -> List[Paper]:
      params = {
          'search_query': f'all:{query}',
          'max_results': max_results,
          'sortBy': 'submittedDate',
          'sortOrder': 'descending'
      }
      response = None
      for attempt in range(3):
          try:
              response = self.session.get(self.BASE_URL, params=params, timeout=30)
          except requests.RequestException:
              time.sleep((attempt + 1) * 1.5)
              continue
          if response.status_code == 200:
              break
          if response.status_code in (429, 500, 502, 503, 504):
              time.sleep((attempt + 1) * 1.5)
              continue
          break
  
      if response is None or response.status_code != 200:
          return []
  
      feed = feedparser.parse(response.content)
      papers = []
      for entry in feed.entries:
          try:
              authors = [author.name for author in entry.authors]
              published = datetime.strptime(entry.published, '%Y-%m-%dT%H:%M:%SZ')
              updated = datetime.strptime(entry.updated, '%Y-%m-%dT%H:%M:%SZ')
              pdf_url = next((link.href for link in entry.links if link.type == 'application/pdf'), '')
              
              # Try to extract DOI from entry.doi or links or summary
              doi = entry.get('doi', '') or extract_doi(entry.summary) or extract_doi(entry.id)
              for link in entry.links:
                  if link.get('title') == 'doi':
                      doi = doi or extract_doi(link.href)
  
              papers.append(Paper(
                  paper_id=entry.id.split('/')[-1],
                  title=entry.title,
                  authors=authors,
                  abstract=entry.summary,
                  url=entry.id,
                  pdf_url=pdf_url,
                  published_date=published,
                  updated_date=updated,
                  source='arxiv',
                  categories=[tag.term for tag in entry.tags],
                  keywords=[],
                  doi=doi
              ))
          except Exception as e:
              print(f"Error parsing arXiv entry: {e}")
      return papers