Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:933-943 (handler)

  The `search_openaire` handler in server.py which calls the `openaire_searcher` helper to perform the search.

  async def search_openaire(query: str, max_results: int = 10) -> List[Dict]:
      """Search academic papers from OpenAIRE European Open Access infrastructure.
  
      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(openaire_searcher, query, max_results)
      return papers if papers else []

• paper_search_mcp/academic_platforms/openaire.py:270-270 (helper)

  The `OpenAiresearcher.search` method in academic_platforms/openaire.py which performs the actual API requests to OpenAIRE.

  def search(self, query: str, max_results: int = 10, **kwargs) -> List[Paper]:

• paper_search_mcp/server.py:300-301 (registration)

  Registration logic where `search_openaire` is called based on the `source` parameter in `server.py`.

  elif source == "openaire":
      task_map[source] = search_openaire(query, max_results_per_source)