Paper Search MCP Server

Instructions

Implementation Reference

• paper_find_mcp/server.py:432-464 (handler)

  MCP tool handler for search_google_scholar. Decorated with @mcp.tool() for registration. Delegates to generic _search using GoogleScholarSearcher.
  @mcp.tool() async def search_google_scholar(query: str, max_results: int = 10) -> List[Dict]: """Search academic papers on Google Scholar (broad coverage). USE THIS TOOL WHEN: - You need broad academic search across ALL disciplines - You want citation counts and "cited by" information - Other specialized tools don't cover your topic COVERAGE: All academic disciplines, books, theses, patents. LIMITATIONS: - Uses web scraping (may be rate-limited) - Does NOT support PDF download FOR FULL TEXT (try in order): 1. download_arxiv(id) - if arXiv preprint 2. download_scihub(doi) - if published before 2023 3. download_semantic(id) - last resort Args: query: Search terms (any academic topic). max_results: Number of results (default: 10, keep small to avoid blocks). Returns: List of paper dicts with: title, authors, abstract snippet, citations count, url, source. Example: search_google_scholar("climate change economic impact", max_results=5) """ return await _search('google_scholar', query, max_results)
• paper_find_mcp/academic_platforms/google_scholar.py:94-143 (helper)

  Core implementation of the search logic in GoogleScholarSearcher class, performing HTTP requests to Google Scholar, parsing HTML with BeautifulSoup, and extracting paper metadata.
  def search(self, query: str, max_results: int = 10) -> List[Paper]: """ Search Google Scholar with custom parameters """ papers = [] start = 0 results_per_page = min(10, max_results) while len(papers) < max_results: try: # Construct search parameters params = { 'q': query, 'start': start, 'hl': 'en', 'as_sdt': '0,5' # Include articles and citations } # Make request with random delay time.sleep(random.uniform(1.0, 3.0)) response = self.session.get(self.SCHOLAR_URL, params=params) if response.status_code != 200: logger.error(f"Search failed with status {response.status_code}") break # Parse results soup = BeautifulSoup(response.text, 'html.parser') results = soup.find_all('div', class_='gs_ri') if not results: break # Process each result for item in results: if len(papers) >= max_results: break paper = self._parse_paper(item) if paper: papers.append(paper) start += results_per_page except Exception as e: logger.error(f"Search error: {e}") break return papers[:max_results]
• paper_find_mcp/server.py:75-85 (registration)

  Instantiation and registration of GoogleScholarSearcher() in the global SEARCHERS dictionary, referenced by the _search helper function.
  SEARCHERS = { 'arxiv': ArxivSearcher(), 'pubmed': PubMedSearcher(), 'biorxiv': BioRxivSearcher(), 'medrxiv': MedRxivSearcher(), 'google_scholar': GoogleScholarSearcher(), 'iacr': IACRSearcher(), 'semantic': SemanticSearcher(), 'crossref': CrossRefSearcher(), 'repec': RePECSearcher(), }
• paper_find_mcp/server.py:95-113 (helper)

  Generic _search helper function that invokes the specific searcher.search() method and converts Paper objects to dicts for the tool response.
  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 []