Paper Search MCP Server

Instructions

Args:
    paper_id: arXiv ID (e.g., '2106.12345').
    save_path: Directory to save PDF (default: ~/paper_downloads).

Returns:
    Full paper text in Markdown format.

Example:
    read_arxiv_paper("2106.12345")

Implementation Reference

• paper_find_mcp/server.py:211-225 (registration)

  Registration of the read_arxiv_paper tool using @mcp.tool() decorator. Defines input schema via type hints and docstring.

  @mcp.tool()
  async def read_arxiv_paper(paper_id: str, save_path: Optional[str] = None) -> str:
      """Download and extract full text from arXiv paper as Markdown.
      
      Args:
          paper_id: arXiv ID (e.g., '2106.12345').
          save_path: Directory to save PDF (default: ~/paper_downloads).
      
      Returns:
          Full paper text in Markdown format.
      
      Example:
          read_arxiv_paper("2106.12345")
      """
      return await _read('arxiv', paper_id, save_path)

• paper_find_mcp/server.py:211-225 (handler)

  Handler function for the read_arxiv_paper MCP tool. Delegates execution to the generic _read helper.

  @mcp.tool()
  async def read_arxiv_paper(paper_id: str, save_path: Optional[str] = None) -> str:
      """Download and extract full text from arXiv paper as Markdown.
      
      Args:
          paper_id: arXiv ID (e.g., '2106.12345').
          save_path: Directory to save PDF (default: ~/paper_downloads).
      
      Returns:
          Full paper text in Markdown format.
      
      Example:
          read_arxiv_paper("2106.12345")
      """
      return await _read('arxiv', paper_id, save_path)

• paper_find_mcp/server.py:137-157 (helper)

  Generic _read helper function that retrieves the appropriate searcher (ArxivSearcher for 'arxiv') and calls its read_paper method.

  async def _read(
      searcher_name: str, 
      paper_id: str, 
      save_path: Optional[str] = None
  ) -> str:
      """通用阅读函数"""
      if save_path is None:
          save_path = get_download_path()
      
      searcher = SEARCHERS.get(searcher_name)
      if not searcher:
          return f"Error: Unknown searcher {searcher_name}"
      
      try:
          return searcher.read_paper(paper_id, save_path)
      except NotImplementedError as e:
          return str(e)
      except Exception as e:
          logger.error(f"Read failed for {searcher_name}: {e}")
          return f"Error reading paper: {str(e)}"

• paper_find_mcp/academic_platforms/arxiv.py:158-196 (helper)

  Core implementation in ArxivSearcher.read_paper: ensures PDF is downloaded, then extracts to Markdown using pymupdf4llm.to_markdown (in _extract_markdown).

  def read_paper(
      self, 
      paper_id: str, 
      save_path: str,
      output_format: Literal["markdown", "text"] = "markdown",
      table_strategy: Literal["lines_strict", "lines", "text", "explicit"] = "lines_strict",
      pages: Optional[List[int]] = None
  ) -> str:
      """读取论文并提取内容
      
      使用 PyMuPDF4LLM 进行高质量文本提取，支持：
      - Markdown 格式输出（推荐，对 LLM 友好）
      - 表格自动转换为 Markdown 表格
      - 多种表格检测策略
      
      Args:
          paper_id: arXiv 论文 ID
          save_path: PDF 存储目录
          output_format: 输出格式
              - "markdown": Markdown 格式（推荐，包含表格）
              - "text": 纯文本格式
          table_strategy: 表格检测策略
              - "lines_strict": 严格模式，只检测有完整边框的表格
              - "lines": 线条模式，检测有部分边框的表格
              - "text": 文本模式，基于对齐检测（适合无边框表格）
              - "explicit": 显式模式，只检测明确标记的表格
          pages: 要提取的页面列表（0-indexed），None 表示全部页面
          
      Returns:
          str: 提取的论文内容
      """
      # 确保 PDF 已下载
      pdf_path = self._ensure_pdf_downloaded(paper_id, save_path)
      
      if output_format == "markdown":
          return self._extract_markdown(pdf_path, table_strategy, pages)
      else:
          return self._extract_text(pdf_path, pages)

• paper_find_mcp/academic_platforms/arxiv.py:116-157 (helper)

  ArxivSearcher.download_pdf method: downloads the arXiv PDF, called indirectly by read_paper via _ensure_pdf_downloaded.

  def download_pdf(self, paper_id: str, save_path: str) -> str:
      """下载 arXiv 论文 PDF
      
      Args:
          paper_id: arXiv 论文 ID (例如 '2106.12345')
          save_path: 保存目录
          
      Returns:
          str: PDF 文件路径
          
      Raises:
          RuntimeError: 下载失败时抛出
      """
      # 确保目录存在
      os.makedirs(save_path, exist_ok=True)
      
      # 构建文件路径
      # 处理带版本号的 ID (例如 2106.12345v2)
      safe_id = paper_id.replace('/', '_').replace(':', '_')
      output_file = os.path.join(save_path, f"{safe_id}.pdf")
      
      # 检查文件是否已存在
      if os.path.exists(output_file):
          logger.info(f"PDF already exists: {output_file}")
          return output_file
      
      # 下载 PDF
      pdf_url = f"https://arxiv.org/pdf/{paper_id}.pdf"
      
      try:
          response = requests.get(pdf_url, timeout=60)
          response.raise_for_status()
          
          with open(output_file, 'wb') as f:
              f.write(response.content)
          
          logger.info(f"PDF downloaded: {output_file}")
          return output_file
          
      except requests.RequestException as e:
          raise RuntimeError(f"Failed to download PDF: {e}")