Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:1017-1029 (handler)

  The 'search_ssrn' handler which delegates the search query to the SSRNSearcher instance.

  async def search_ssrn(query: str, max_results: int = 10) -> List[Dict]:
      """Search metadata records from SSRN.
  
      Note: SSRN connector is metadata-only and does not support direct PDF download.
  
      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(ssrn_searcher, query, max_results)
      return papers if papers else []

• paper_search_mcp/academic_platforms/ssrn.py:71-104 (handler)

  The implementation of the search method within the SSRNSearcher class that performs the actual web request and parsing.

  def search(self, query: str, max_results: int = 10, **kwargs) -> List[Paper]:
      """Search SSRN and return metadata records.
  
      Args:
          query: Search terms.
          max_results: Maximum results to return (practical limit ~30 without
                       pagination; SSRN returns ~15 results per page).
          **kwargs: Unused; reserved for future filter support.
  
      Returns:
          List of :class:`~paper_search_mcp.paper.Paper` objects.
      """
      papers: List[Paper] = []
      page = 1
      per_page = 15  # SSRN default
  
      while len(papers) < max_results:
          self._throttle()
          html, err = self._fetch_page(query, page)
          if err or not html:
              logger.warning("SSRN search page %d fetch failed: %s", page, err)
              break
  
          page_papers = self._parse_results(html)
          if not page_papers:
              break
  
          papers.extend(page_papers)
          if len(page_papers) < per_page:
              break  # last page
  
          page += 1
  
      return papers[:max_results]

• paper_search_mcp/server.py:313-313 (registration)

  The registration of the search_ssrn tool in the main server task map.

  task_map[source] = search_ssrn(query, max_results_per_source)