Paper Search MCP Server

Instructions

USE THIS TOOL WHEN:
- You have a DOI and need full metadata (title, authors, journal, etc.)
- You want to verify a DOI exists
- You need citation count for a specific paper

Args:
    doi: Digital Object Identifier (e.g., '10.1038/nature12373').

Returns:
    Paper metadata dict, or empty dict {} if DOI not found.

Example:
    get_crossref_paper_by_doi("10.1038/nature12373")

Implementation Reference

• paper_find_mcp/server.py:659-684 (handler)

  MCP tool handler and registration. Retrieves CrossRef paper by DOI using the CrossRefSearcher instance, converts Paper to dict.

  @mcp.tool()
  async def get_crossref_paper_by_doi(doi: str) -> Dict:
      """Get paper metadata from CrossRef using its DOI.
      
      USE THIS TOOL WHEN:
      - You have a DOI and need full metadata (title, authors, journal, etc.)
      - You want to verify a DOI exists
      - You need citation count for a specific paper
      
      Args:
          doi: Digital Object Identifier (e.g., '10.1038/nature12373').
      
      Returns:
          Paper metadata dict, or empty dict {} if DOI not found.
      
      Example:
          get_crossref_paper_by_doi("10.1038/nature12373")
      """
      searcher = SEARCHERS['crossref']
      try:
          paper = searcher.get_paper_by_doi(doi)
          return paper.to_dict() if paper else {}
      except Exception as e:
          logger.error(f"CrossRef DOI lookup failed: {e}")
          return {}

• paper_find_mcp/academic_platforms/crossref.py:339-371 (helper)

  Core implementation in CrossRefSearcher: queries CrossRef API /works/{doi}, parses response into Paper object using _parse_crossref_item.

  def get_paper_by_doi(self, doi: str) -> Optional[Paper]:
      """
      Get a specific paper by DOI.
      
      Args:
          doi: Digital Object Identifier
          
      Returns:
          Paper object if found, None otherwise
      """
      try:
          url = f"{self.BASE_URL}/works/{doi}"
          params = {'mailto': 'paper-search@example.org'}
          
          response = self.session.get(url, params=params, timeout=30)
          
          if response.status_code == 404:
              logger.warning(f"DOI not found in CrossRef: {doi}")
              return None
              
          response.raise_for_status()
          data = response.json()
          
          item = data.get('message', {})
          return self._parse_crossref_item(item)
          
      except requests.RequestException as e:
          logger.error(f"Error fetching DOI {doi} from CrossRef: {e}")
          return None
      except Exception as e:
          logger.error(f"Unexpected error fetching DOI {doi}: {e}")
          return None

• paper_find_mcp/server.py:75-85 (helper)

  Global SEARCHERS dictionary instantiates and registers the CrossRefSearcher singleton used by the get_crossref_paper_by_doi tool.

  SEARCHERS = {
      'arxiv': ArxivSearcher(),
      'pubmed': PubMedSearcher(),
      'biorxiv': BioRxivSearcher(),
      'medrxiv': MedRxivSearcher(),
      'google_scholar': GoogleScholarSearcher(),
      'iacr': IACRSearcher(),
      'semantic': SemanticSearcher(),
      'crossref': CrossRefSearcher(),
      'repec': RePECSearcher(),
  }