Skip to main content
Glama
pdfdotco

PDF.co MCP Server

Official
by pdfdotco

ai_invoice_parser

Extract structured data from invoices using AI to automate data entry and processing tasks.

Instructions

AI Invoice Parser: Extracts data from invoices using AI. Ref: https://developer.pdf.co/api-reference/ai-invoice-parser.md

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesURL 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.
api_keyNoPDF.co API key. If not provided, will use X_API_KEY environment variable. (Optional)

Implementation Reference

  • The core handler function for the 'ai_invoice_parser' tool, registered via @mcp.tool() decorator. Defines input schema (url and optional api_key) using Pydantic Field for descriptions and validation. Prepares ConversionParams and delegates to parse_invoice helper for API execution.
    @mcp.tool() async def ai_invoice_parser( 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." ), api_key: str = Field( description="PDF.co API key. If not provided, will use X_API_KEY environment variable. (Optional)", default="", ), ) -> BaseResponse: """ AI Invoice Parser: Extracts data from invoices using AI. Ref: https://developer.pdf.co/api-reference/ai-invoice-parser.md """ # Pass arguments directly; ConversionParams now handles str with default=None params = ConversionParams( url=url, ) return await parse_invoice(params, api_key=api_key)
  • Helper function that performs the specific HTTP request to the PDF.co 'ai-invoice-parser' API endpoint using the general request function.
    async def parse_invoice(params: ConversionParams, api_key: str | None = None) -> BaseResponse: return await request("ai-invoice-parser", params, api_key=api_key)
  • General-purpose HTTP request helper used by parse_invoice (and other tools) to call PDF.co API endpoints asynchronously, handling payload preparation, client usage, response parsing, and error handling.
    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]}", )

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pdfdotco/pdfco-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server