PDF.co MCP Server

Instructions

Implementation Reference

• pdfco/mcp/tools/apis/searchable.py:8-56 (handler)

  The core handler function for the 'pdf_make_searchable' tool. It is registered as an MCP tool via the @mcp.tool() decorator, defines the input schema using Pydantic Field descriptions, and implements the logic by constructing ConversionParams and delegating to the service layer.
  @mcp.tool() async def pdf_make_searchable( 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." ), 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="", ), 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", ), 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="", ), password: str = Field( description="Password of the PDF file. (Optional)", default="" ), name: str = Field( description="File name for the generated output. (Optional)", default="" ), api_key: str = Field( description="PDF.co API key. If not provided, will use X_API_KEY environment variable. (Optional)", default="", ), ) -> BaseResponse: """ Convert scanned PDF documents or image files into a text-searchable PDF. Runs OCR and adds an invisible text layer that can be used for text search. Ref: https://developer.pdf.co/api-reference/pdf-change-text-searchable/searchable.md """ params = ConversionParams( url=url, httpusername=httpusername, httppassword=httppassword, lang=lang, pages=pages, password=password, name=name, ) return await make_pdf_searchable(params, api_key=api_key)
• pdfco/mcp/services/pdf.py:85-88 (helper)

  Supporting helper function that performs the actual API call to PDF.co's 'pdf/makesearchable' endpoint via the generic request function.
  async def make_pdf_searchable( params: ConversionParams, api_key: str | None = None ) -> BaseResponse: return await request("pdf/makesearchable", params, api_key=api_key)
• pdfco/mcp/models.py:5-11 (schema)

  Pydantic model for the tool's output response.
  class BaseResponse(BaseModel): status: str content: Any credits_used: int | None = None credits_remaining: int | None = None tips: str | None = None
• pdfco/mcp/models.py:12-105 (schema)

  Pydantic model defining input parameters for PDF conversion tools, including those used by pdf_make_searchable. Note: excerpt truncated for brevity; full class includes more fields and parse_payload method.
  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="" )
• pdfco/mcp/services/pdf.py:125-154 (helper)

  Core helper function that handles HTTP requests to the PDF.co API, used by make_pdf_searchable.
  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]}", )