Academic Paper Search MCP Server

Instructions

Args:
    paper_id: Paper identifier (DOI for Crossref, paper ID for Semantic Scholar)
    source: Source database ("semantic_scholar" or "crossref")

Implementation Reference

• server.py:134-158 (handler)

  The main handler function for the 'fetch_paper_details' tool. It constructs the appropriate API URL based on the source, fetches the data using make_api_request, handles Crossref response structure, and formats the output using format_paper_data. Registered via @mcp.tool() decorator.

  @mcp.tool()
  async def fetch_paper_details(paper_id: str, source: str = "semantic_scholar") -> str:
      """Get detailed information about a specific paper.
  
      Args:
          paper_id: Paper identifier (DOI for Crossref, paper ID for Semantic Scholar)
          source: Source database ("semantic_scholar" or "crossref")
      """
      if source == "semantic_scholar":
          url = f"{SEMANTIC_SCHOLAR_API}/paper/{paper_id}"
      elif source == "crossref":
          url = f"{CROSSREF_API}/{paper_id}"
      else:
          return "Unsupported source. Please use 'semantic_scholar' or 'crossref'."
  
      data = await make_api_request(url)
      
      if not data:
          return f"Unable to fetch paper details from {source}."
  
      if source == "crossref":
          data = data.get('message', {})
  
      return format_paper_data(data, source)

• server.py:26-37 (helper)

  Helper function to make HTTP requests to the Semantic Scholar or Crossref APIs with error handling and timeout.

  async def make_api_request(url: str, headers: dict = None, params: dict = None) -> dict[str, Any] | None:
      """Make a request to the API with proper error handling."""
      if headers is None:
          headers = { "User-Agent": USER_AGENT }
      async with httpx.AsyncClient() as client:
          try:
              response = await client.get(url, headers=headers, params=params, timeout=30.0)
              response.raise_for_status()
              return response.json()
          except Exception as e:
              return None

• server.py:38-86 (helper)

  Helper function that formats the raw API response data from either source into a consistent human-readable string format, handling fields like title, authors, year, DOI, and source-specific fields.

  def format_paper_data(data: dict, source: str) -> str:
      """Format paper data from different sources into a consistent string format."""
      if not data:
          return "No paper data available"
          
      try:
          if source == "semantic_scholar":
              title = unicodedata.normalize('NFKD', str(data.get('title', 'No title available')))
              authors = ', '.join([author.get('name', 'Unknown Author') for author in data.get('authors', [])])
              year = data.get('year') or 'Year unknown'
              external_ids = data.get('externalIds', {}) or {}
              doi = external_ids.get('DOI', 'No DOI available')
              venue = data.get('venue') or 'Venue unknown'
              abstract = data.get('abstract') or 'No abstract available'
              tldr = (data.get('tldr') or {}).get('text', '')
              is_open = "Yes" if data.get('isOpenAccess') else "No"
              pdf_data = data.get('openAccessPdf', {}) or {}
              pdf_url = pdf_data.get('url', 'Not available')
  
          elif source == "crossref":
              title = (data.get('title') or ['No title available'])[0]
              authors = ', '.join([
                  f"{author.get('given', '')} {author.get('family', '')}".strip() or 'Unknown Author'
                  for author in data.get('author', [])
              ])
              year = (data.get('published-print', {}).get('date-parts', [['']])[0][0]) or 'Year unknown'
              doi = data.get('DOI') or 'No DOI available'
              
          result = [
              f"Title: {title}",
              f"Authors: {authors}",
              f"Year: {year}",
              f"DOI: {doi}"
          ]
          
          if source == "semantic_scholar":
              result.extend([
                  f"Venue: {venue}",
                  f"Open Access: {is_open}",
                  f"PDF URL: {pdf_url}",
                  f"Abstract: {abstract}"
              ])
              if tldr:
                  result.append(f"TL;DR: {tldr}")
                  
          return "\n".join(result) + "\t\t\n"
          
      except Exception as e:
          return f"Error formatting paper data: {str(e)}"

• server.py:134-134 (registration)

  The @mcp.tool() decorator registers the fetch_paper_details function as an MCP tool.

  @mcp.tool()