Paper Search MCP Server

Instructions

USE THIS TOOL WHEN:
- You want to search across ALL academic disciplines
- You need citation counts and influence metrics
- You want to filter by publication year
- You need open-access PDF links when available

COVERAGE: ALL academic fields - sciences, humanities, medicine, etc.
Indexes 200M+ papers from journals, conferences, and preprints.

WORKFLOW:
1. search_semantic(query) -> get paper_id or DOI
2. download_semantic(paper_id) -> get PDF (if open-access)
3. If no PDF: use download_scihub(doi) for older papers

Args:
    query: Search terms (any topic, any field).
    year: Optional year filter: '2023', '2020-2023', '2020-', '-2019'.
    max_results: Number of results (default: 10).

Returns:
    List of paper dicts with: paper_id, title, authors, abstract,
    published_date, doi, citations, url, pdf_url (if available).

Example:
    search_semantic("climate change impact agriculture", year="2020-", max_results=5)

Implementation Reference

• paper_find_mcp/server.py:547-581 (handler)

  Primary handler and registration for the 'search_semantic' tool. Defines input schema via type hints and docstring. Delegates to _search('semantic', ...) using the SemanticSearcher instance.

  @mcp.tool()
  async def search_semantic(
      query: str, year: Optional[str] = None, max_results: int = 10
  ) -> List[Dict]:
      """Search papers on Semantic Scholar - general-purpose academic search engine.
      
      USE THIS TOOL WHEN:
      - You want to search across ALL academic disciplines
      - You need citation counts and influence metrics
      - You want to filter by publication year
      - You need open-access PDF links when available
      
      COVERAGE: ALL academic fields - sciences, humanities, medicine, etc.
      Indexes 200M+ papers from journals, conferences, and preprints.
      
      WORKFLOW:
      1. search_semantic(query) -> get paper_id or DOI
      2. download_semantic(paper_id) -> get PDF (if open-access)
      3. If no PDF: use download_scihub(doi) for older papers
      
      Args:
          query: Search terms (any topic, any field).
          year: Optional year filter: '2023', '2020-2023', '2020-', '-2019'.
          max_results: Number of results (default: 10).
      
      Returns:
          List of paper dicts with: paper_id, title, authors, abstract,
          published_date, doi, citations, url, pdf_url (if available).
      
      Example:
          search_semantic("climate change impact agriculture", year="2020-", max_results=5)
      """
      kwargs = {'year': year} if year else {}
      return await _search('semantic', query, max_results, **kwargs)

• paper_find_mcp/server.py:95-113 (helper)

  Generic helper function used by search_semantic (and other tools) to invoke the searcher.search() method and convert results to dicts.

  async def _search(
      searcher_name: str, 
      query: str, 
      max_results: int = 10,
      **kwargs
  ) -> List[Dict]:
      """通用搜索函数"""
      searcher = SEARCHERS.get(searcher_name)
      if not searcher:
          logger.error(f"Unknown searcher: {searcher_name}")
          return []
      
      try:
          papers = searcher.search(query, max_results=max_results, **kwargs)
          return [paper.to_dict() for paper in papers]
      except Exception as e:
          logger.error(f"Search failed for {searcher_name}: {e}")
          return []

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

  Global SEARCHERS dictionary that instantiates SemanticSearcher() for the 'semantic' key, used by _search.

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

• paper_find_mcp/academic_platforms/semantic.py:245-289 (helper)

  Core implementation of semantic search logic in SemanticSearcher.search(): queries Semantic Scholar API, handles rate limiting, parses results into Paper objects.

  def search(
      self, 
      query: str, 
      year: Optional[str] = None, 
      max_results: int = 10
  ) -> List[Paper]:
      """搜索论文
      
      Args:
          query: 搜索关键词
          year: 年份过滤（支持格式："2019", "2016-2020", "2010-", "-2015"）
          max_results: 最大返回数量
          
      Returns:
          List[Paper]: 论文列表
      """
      params = {
          "query": query,
          "limit": min(max_results, 100),  # API 限制
          "fields": ",".join(self.DEFAULT_FIELDS),
      }
      
      if year:
          params["year"] = year
      
      response = self._make_request("paper/search", params)
      if not response:
          return []
      
      try:
          data = response.json()
          results = data.get('data', [])
      except Exception as e:
          logger.error(f"Failed to parse response: {e}")
          return []
      
      papers = []
      for item in results[:max_results]:
          paper = self._parse_paper(item)
          if paper:
              papers.append(paper)
      
      logger.info(f"Found {len(papers)} papers for query: {query}")
      return papers