PDF.co MCP Server

Instructions

Find tables in PDF and get their coordinates.
Ref: https://developer.pdf.co/api-reference/pdf-find/table.md

Implementation Reference

• pdfco/mcp/tools/apis/search.py:61-98 (handler)

  The primary handler for the 'find_table' MCP tool. Includes registration via @mcp.tool decorator, input schema definition using pydantic Field descriptions, parameter processing into ConversionParams, and delegation to the find_table_in_pdf helper.

  @mcp.tool(name="find_table")
  async def find_table(
      url: str = Field(
          description="URL to the source PDF file. Supports publicly accessible links including Google Drive, Dropbox, PDF.co Built-In Files Storage. Use 'upload_file' tool to upload local files."
      ),
      httpusername: str = Field(
          description="HTTP auth user name if required to access source url. (Optional)",
          default="",
      ),
      httppassword: str = Field(
          description="HTTP auth password if required to access source url. (Optional)",
          default="",
      ),
      pages: str = Field(
          description="Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'. The first-page index is 0. (Optional)",
          default="",
      ),
      password: str = Field(
          description="Password of the PDF file. (Optional)", default=""
      ),
      api_key: str = Field(
          description="PDF.co API key. If not provided, will use X_API_KEY environment variable. (Optional)",
          default="",
      ),
  ) -> BaseResponse:
      """
      Find tables in PDF and get their coordinates.
      Ref: https://developer.pdf.co/api-reference/pdf-find/table.md
      """
      params = ConversionParams(
          url=url,
          httpusername=httpusername,
          httppassword=httppassword,
          pages=pages,
          password=password,
      )
  
      return await find_table_in_pdf(params, api_key=api_key)

• pdfco/mcp/services/pdf.py:79-82 (helper)

  Helper function that executes the core logic by making an asynchronous request to the PDF.co API endpoint for finding tables in PDFs.

  async def find_table_in_pdf(
      params: ConversionParams, api_key: str | None = None
  ) -> BaseResponse:
      return await request("pdf/find/table", params, api_key=api_key)