Paper Search MCP Server

Instructions

USE THIS TOOL WHEN:
- Searching for cryptography or security research
- You need papers on encryption, blockchain, zero-knowledge proofs
- Looking for security protocols, hash functions, signatures

DOMAIN: Cryptography ONLY - encryption, signatures, protocols,
blockchain, secure computation, zero-knowledge, hash functions.

All papers are FREE and open access with PDF download.

WORKFLOW:
1. search_iacr(query) -> get paper_id (e.g., '2024/123')
2. download_iacr(paper_id) or read_iacr_paper(paper_id)

Args:
    query: Crypto terms (e.g., 'zero knowledge', 'homomorphic encryption').
    max_results: Number of results (default: 10).
    fetch_details: Get full metadata per paper (default: True).

Returns:
    List of paper dicts with: paper_id, title, authors, abstract,
    published_date, pdf_url.

Example:
    search_iacr("post-quantum cryptography", max_results=5)

Implementation Reference

• paper_find_mcp/server.py:469-508 (handler)

  Primary MCP tool handler for 'search_iacr'. Delegates to IACRSearcher instance via SEARCHERS['iacr'].search() method.

  @mcp.tool()
  async def search_iacr(
      query: str, max_results: int = 10, fetch_details: bool = True
  ) -> List[Dict]:
      """Search cryptography papers on IACR ePrint Archive.
      
      USE THIS TOOL WHEN:
      - Searching for cryptography or security research
      - You need papers on encryption, blockchain, zero-knowledge proofs
      - Looking for security protocols, hash functions, signatures
      
      DOMAIN: Cryptography ONLY - encryption, signatures, protocols,
      blockchain, secure computation, zero-knowledge, hash functions.
      
      All papers are FREE and open access with PDF download.
      
      WORKFLOW:
      1. search_iacr(query) -> get paper_id (e.g., '2024/123')
      2. download_iacr(paper_id) or read_iacr_paper(paper_id)
      
      Args:
          query: Crypto terms (e.g., 'zero knowledge', 'homomorphic encryption').
          max_results: Number of results (default: 10).
          fetch_details: Get full metadata per paper (default: True).
      
      Returns:
          List of paper dicts with: paper_id, title, authors, abstract,
          published_date, pdf_url.
      
      Example:
          search_iacr("post-quantum cryptography", max_results=5)
      """
      searcher = SEARCHERS['iacr']
      try:
          papers = searcher.search(query, max_results, fetch_details)
          return [paper.to_dict() for paper in papers] if papers else []
      except Exception as e:
          logger.error(f"IACR search failed: {e}")
          return []

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

  Global SEARCHERS dictionary instantiation including 'iacr': IACRSearcher() used by the handler.

  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:32-32 (helper)

  Import of IACRSearcher class.

  from .academic_platforms.iacr import IACRSearcher

• paper_find_mcp/academic_platforms/iacr.py:154-205 (handler)

  Core search logic in IACRSearcher.search(): performs HTTP search on eprint.iacr.org, parses HTML results with BeautifulSoup, optionally fetches details per paper.

  def search(
      self, query: str, max_results: int = 10, fetch_details: bool = True
  ) -> List[Paper]:
      """
      Search IACR ePrint Archive
  
      Args:
          query: Search query string
          max_results: Maximum number of results to return
          fetch_details: Whether to fetch detailed information for each paper (slower but more complete)
  
      Returns:
          List[Paper]: List of paper objects
      """
      papers = []
  
      try:
          # Construct search parameters
          params = {"q": query}
  
          # Make request
          response = self.session.get(self.IACR_SEARCH_URL, params=params)
  
          if response.status_code != 200:
              logger.error(f"IACR search failed with status {response.status_code}")
              return papers
  
          # Parse results
          soup = BeautifulSoup(response.text, "html.parser")
  
          # Find all paper entries - they are divs with class "mb-4"
          results = soup.find_all("div", class_="mb-4")
  
          if not results:
              logger.info("No results found for the query")
              return papers
  
          # Process each result
          for i, item in enumerate(results):
              if len(papers) >= max_results:
                  break
  
              logger.info(f"Processing paper {i+1}/{min(len(results), max_results)}")
              paper = self._parse_paper(item, fetch_details=fetch_details)
              if paper:
                  papers.append(paper)
  
      except Exception as e:
          logger.error(f"IACR search error: {e}")
  
      return papers[:max_results]

• paper_find_mcp/server.py:470-472 (schema)

  Function signature defines input schema (query:str, max_results:int=10, fetch_details:bool=True) and output List[Dict] for MCP tool schema inference.

  async def search_iacr(
      query: str, max_results: int = 10, fetch_details: bool = True
  ) -> List[Dict]: