Paper Search MCP Server

Instructions

Implementation Reference

• paper_find_mcp/server.py:304-335 (handler)

  The MCP tool handler for search_biorxiv. Decorated with @mcp.tool() for registration. Defines input schema (query: str, max_results: int=10) and delegates to _search('biorxiv', ...) using the BioRxivSearcher instance.
  @mcp.tool() async def search_biorxiv(query: str, max_results: int = 10) -> List[Dict]: """Search biology preprints on bioRxiv. USE THIS TOOL WHEN: - Searching for cutting-edge biology research (preprints) - You need the latest findings before peer review - Searching by CATEGORY, not keyword (see below) DOMAIN: Molecular Biology, Cell Biology, Genetics, Neuroscience, Bioinformatics, Evolutionary Biology, Microbiology, etc. NOTE: bioRxiv search uses CATEGORY names, not keywords. Categories: 'neuroscience', 'cell_biology', 'genetics', 'genomics', 'bioinformatics', 'cancer_biology', 'immunology', etc. WORKFLOW: 1. search_biorxiv(category) -> get DOI 2. download_biorxiv(doi) or read_biorxiv_paper(doi) Args: query: Category name (e.g., 'neuroscience', 'cell_biology'). max_results: Number of results (default: 10). Returns: List of recent preprints in that category. Example: search_biorxiv("neuroscience", max_results=5) """ return await _search('biorxiv', query, max_results)
• paper_find_mcp/academic_platforms/biorxiv.py:92-145 (helper)

  Core implementation of the search logic in BioRxivSearcher.search(). Queries bioRxiv API with category filter, paginates results, parses into Paper objects with rate limiting and retries.
  def search(self, query: str, max_results: int = 10, days: int = 30) -> List[Paper]: """搜索 bioRxiv 论文 Args: query: 分类名称（如 "cell biology", "neuroscience"） max_results: 最大返回数量 days: 搜索最近 N 天的论文 Returns: List[Paper]: 论文列表 """ end_date = datetime.now().strftime('%Y-%m-%d') start_date = (datetime.now() - timedelta(days=days)).strftime('%Y-%m-%d') # 格式化分类 category = query.lower().replace(' ', '_') papers = [] cursor = 0 while len(papers) < max_results: url = f"{self.BASE_URL}/{start_date}/{end_date}/{cursor}" if category: url += f"?category={category}" response = self._make_request(url) if not response: break try: data = response.json() collection = data.get('collection', []) except Exception as e: logger.error(f"Failed to parse response: {e}") break if not collection: break for item in collection: if len(papers) >= max_results: break paper = self._parse_item(item) if paper: papers.append(paper) if len(collection) < 100: break # 没有更多结果 cursor += 100 logger.info(f"Found {len(papers)} papers for query: {query}") return papers[:max_results]
• paper_find_mcp/server.py:75-85 (helper)

  Global SEARCHERS dictionary instantiates singleton BioRxivSearcher() instance mapped to 'biorxiv' key, used by _search to dispatch calls.
  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 called by search_biorxiv handler. Retrieves BioRxivSearcher by name, invokes its search method, converts Papers 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 []