find_table

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:61-62 (registration)

  Tool registration via @mcp.tool(name="find_table") decorator on the find_table async function.

  @mcp.tool(name="find_table")
  async def find_table(

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

  Handler function for the find_table MCP tool. Accepts a PDF URL, optional auth credentials, pages, password, and API key. Constructs a ConversionParams object and delegates to find_table_in_pdf service function.

  @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)

  Service-level helper that makes the actual API call to the "pdf/find/table" endpoint via the shared request() function.

  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)

• pdfco/mcp/services/pdf.py:125-153 (helper)

  Generic HTTP helper that builds the payload, calls the PDF.co API via PDFCoClient, and returns a BaseResponse with job status info.

  async def request(
      endpoint: str,
      params: ConversionParams,
      custom_payload: dict | None = None,
      api_key: str | None = None,
  ) -> BaseResponse:
      payload = params.parse_payload(async_mode=True)
      if custom_payload:
          payload.update(custom_payload)
  
      try:
          async with PDFCoClient(api_key=api_key) as client:
              url = f"/v1/{endpoint}"
              print(f"Requesting {url} with payload {payload}", file=sys.stderr)
              response = await client.post(url, json=payload)
              print(f"response: {response}", file=sys.stderr)
              json_data = response.json()
              return BaseResponse(
                  status="working",
                  content=json_data,
                  credits_used=json_data.get("credits"),
                  credits_remaining=json_data.get("remainingCredits"),
                  tips=f"You **should** use the 'wait_job_completion' tool to wait for the job [{json_data.get('jobId')}] to complete if a jobId is present.",
              )
      except Exception as e:
          return BaseResponse(
              status="error",
              content=f"{type(e)}: {[arg for arg in e.args if arg]}",
          )

• pdfco/mcp/models.py:13-105 (schema)

  Input schema (ConversionParams) used by find_table. Defines fields like url, httpusername, httppassword, pages, password, and includes parse_payload() to build the API request body.

  class ConversionParams(BaseModel):
      url: str = Field(
          description="URL to the source file. Supports publicly accessible links including Google Drive, Dropbox, PDF.co Built-In Files Storage. Use 'upload_file' tool to upload local files.",
          default="",
      )
      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 page indices (e.g., '0, 1, 2-' or '1, 3-7'). Use '!' for inverted page numbers (e.g., '!0' for last page). Processes all pages if None. (Optional)",
          default="",
      )
      unwrap: bool = Field(
          description="Unwrap lines into a single line within table cells when lineGrouping is enabled. Must be true or false. (Optional)",
          default=False,
      )
      rect: str = Field(
          description="Defines coordinates for extraction (e.g., '51.8,114.8,235.5,204.0'). (Optional)",
          default="",
      )
      lang: str = Field(
          description="Language for OCR for scanned documents. Default is 'eng'. See PDF.co docs for supported languages. (Optional, Default: 'eng')",
          default="eng",
      )
      line_grouping: str = Field(
          description="Enables line grouping within table cells when set to '1'. (Optional)",
          default="0",
      )
      password: str = Field(
          description="Password of the PDF file. (Optional)", default=""
      )
      name: str = Field(
          description="File name for the generated output. (Optional)", default=""
      )
      autosize: bool = Field(
          description="Controls automatic page sizing. If true, page dimensions adjust to content. If false, uses worksheet’s page setup. (Optional)",
          default=False,
      )
  
      html: str = Field(
          description="Input HTML code to be converted. To convert the link to a PDF use the /pdf/convert/from/url endpoint instead.",
          default="",
      )
      templateId: str = Field(
          description="Set to the ID of your HTML template. You can find and copy the ID from HTML to PDF Templates.",
          default="",
      )
      templateData: str = Field(
          description="Set it to a string with input JSON data (recommended) or CSV data.",
          default="",
      )
      margins: str = Field(
          description="Set to CSS style margins like 10px, 5mm, 5in for all sides or 5px 5px 5px 5px (the order of margins is top, right, bottom, left). (Optional)",
          default="",
      )
      paperSize: str = Field(
          description="A4 is set by default. Can be Letter, Legal, Tabloid, Ledger, A0, A1, A2, A3, A4, A5, A6 or a custom size. Custom size can be set in px (pixels), mm or in (inches) with width and height separated by space like this: 200 300, 200px 300px, 200mm 300mm, 20cm 30cm or 6in 8in. (Optional)",
          default="",
      )
      orientation: str = Field(
          description="Set to Portrait or Landscape. Portrait is set by default. (Optional)",
          default="",
      )
      printBackground: bool = Field(
          description="true by default. Set to false to disable printing of background. (Optional)",
          default=True,
      )
      mediaType: str = Field(
          description="Uses print by default. Set to screen to convert HTML as it appears in a browser or print to convert as it appears for printing or none to set none as mediaType for CSS styles. (Optional)",
          default="",
      )
      DoNotWaitFullLoad: bool = Field(
          description="false by default. Set to true to skip waiting for full load (like full video load etc. that may affect the total conversion time). (Optional)",
          default=False,
      )
      header: str = Field(
          description="User definable HTML for the header to be applied on every page header. (Optional)",
          default="",
      )
      footer: str = Field(
          description="User definable HTML for the footer to be applied on every page footer. (Optional)",
          default="",
      )
  
      worksheetIndex: str = Field(
          description="Index of the worksheet to convert. (Optional)", default=""
      )