ai_invoice_parser
AI Invoice Parser: Extracts data from invoices using AI. Ref: https://developer.pdf.co/api/ai-invoice-parser.md
LABSCO SUMMARY
Document plumbing an agent can drive without a file handler of its own.
The value is coverage: nearly every crossing between PDF, spreadsheet, image, web page and email has a tool, so a chain like scan to OCR to CSV never leaves the conversation. Two habits matter when driving it — long conversions return a job rather than a result, so pair them with wait_job_completion, and find_text returns coordinates rather than text, which is what makes annotation and form placement possible.
What it is
A client for the PDF.co document API, covering conversion in both directions, OCR, form handling, search by coordinate and file assembly. Long operations run as background jobs you poll or wait on.
What you get
- A PDF read out in whatever shape the next step needs: JSON with fonts, images, vectors and formatting preserved, CSV with columns and rows, plain text with layout, XLS or XLSX, XML, HTML, or page images as JPG, PNG, WebP or TIFF (pdf_to_json, pdf_to_csv, pdf_to_text, pdf_to_xls, pdf_to_xlsx, pdf_to_xml, pdf_to_html, pdf_to_image).
- A PDF built from almost anything: DOC, DOCX, RTF, TXT, XLS, XLSX, CSV, HTML and images, plus a live webpage URL, an HTML string with header and footer markup, or an email (document_to_pdf, csv_to_pdf, image_to_pdf, webpage_to_pdf, html_to_pdf, email_to_pdf).
- Excel converted straight out to CSV, JSON, HTML, TXT, XML or PDF without going through a PDF first (excel_to_csv, excel_to_json, excel_to_html, excel_to_txt, excel_to_xml, excel_to_pdf).
- Form work end to end: read the fillable field names out of a document, fill them by name, or add new form elements at chosen coordinates (read_pdf_forms_info, fill_forms, create_fillable_forms).
- Text and table locations returned as coordinates, with regular expressions supported on the text search — the input for annotating or redacting a specific spot (find_text, find_table).
- OCR that adds an invisible text layer to a scan, and the reverse for stripping one out (pdf_make_searchable, pdf_make_unsearchable).
- Assembly and access control: merge PDFs, DOCs, XLS files, images or a ZIP of them into one document, split by page index or range, add or remove a password (pdf_merge, pdf_split, pdf_add_password, pdf_remove_password).
- Document inspection and extraction: page count, metadata, security state and form fields, attachments pulled out of a PDF, and an AI parser that reads invoice data (pdf_info_reader, extract_attachments, ai_invoice_parser).
- Job control for the asynchronous side: upload a local file to the API, check whether a job is working, success, failed, aborted or unknown, or block until it finishes (upload_file, get_job_check, wait_job_completion).
Requirements
A PDF.co account and its API key, passed as X_API_KEY. UV supplies the runtime — install it, then launch with uvx pdfco-mcp over stdio.
Setup effort
One command plus a key — uvx pdfco-mcp, then supply credentials
USE CASES
01
Getting a table out of a PDF report into a spreadsheet
Locate the tables by coordinate first when the layout is awkward, then convert to CSV or XLSX.
02
Making an old scan searchable
Run OCR to add an invisible text layer, then confirm the words are really there by searching for one.
03
Processing a stack of supplier invoices
Let the AI parser read the fields instead of writing a regex per vendor template.
04
Filling a form you were sent as a PDF
Read the field names out of the document first — filling by guessed name is what fails.
05
Turning a web page into a document you can archive
Render the URL to PDF with your own header and footer markup, then lock it.
06
Assembling one deliverable out of mixed files
Merge PDFs, spreadsheets and images into a single document, then split off the section someone asked for.
38 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
create_fillable_forms
Create new fillable form elements in a PDF document.
Example annotations format: [ { "text": "prefilled text", "x": 10, "y": 30, "size": 12, "pages": "0-", "type": "TextField", "id": "textfield1" }, { "x": 100, "y": 150, "size": 12, "pages": "0-", "type": "Checkbox", "id": "checkbox1" } ]
Ref: https://developer.pdf.co/api/pdf-add.md
csv_to_pdf
Convert CSV or spreadsheet files (XLS, XLSX) to PDF. Ref: https://developer.pdf.co/api/pdf-from-document/csv.md
document_to_pdf
Convert various document types (DOC, DOCX, RTF, TXT, XLS, XLSX, CSV, HTML, JPG, PNG, TIFF, WEBP) into PDF. Ref: https://developer.pdf.co/api/pdf-from-document/doc.md
email_to_pdf
Convert email to PDF. Ref: https://developer.pdf.co/api/pdf-from-email.md
excel_to_csv
Convert Excel(XLS, XLSX) to CSV. Ref: https://developer.pdf.co/api/convert-from-excel/csv.md
excel_to_html
Convert Excel(XLS, XLSX) to HTML. Ref: https://developer.pdf.co/api/convert-from-excel/html.md
excel_to_json
Convert Excel(XLS, XLSX) to JSON. Ref: https://developer.pdf.co/api/convert-from-excel/json.md
excel_to_pdf
Convert Excel(XLS, XLSX) to PDF. Ref: https://developer.pdf.co/api/convert-from-excel/pdf.md
excel_to_txt
Convert Excel(XLS, XLSX) to TXT. Ref: https://developer.pdf.co/api/convert-from-excel/text.md
excel_to_xml
Convert Excel(XLS, XLSX) to XML. Ref: https://developer.pdf.co/api/convert-from-excel/xml.md
extract_attachments
Extracts attachments from a source PDF file. Ref: https://developer.pdf.co/api/pdf-extract-attachments.md
fill_forms
Fill existing form fields in a PDF document.
Example fields format: [ { "fieldName": "field_name_from_form_info", "pages": "1", "text": "Value to fill" } ]
Use 'read_pdf_forms_info' first to get the fieldName values of the form.
Ref: https://developer.pdf.co/api/pdf-add.md
find_table
Find tables in PDF and get their coordinates. Ref: https://developer.pdf.co/api/pdf-find/table.md
find_text
Find text in PDF and get coordinates. Supports regular expressions. Ref: https://developer.pdf.co/api/pdf-find/basic.md
get_job_check
Check the status and results of a job Status can be:
- working: background job is currently in work or does not exist.
- success: background job was successfully finished.
- failed: background job failed for some reason (see message for more details).
- aborted: background job was aborted.
- unknown: unknown background job id. Available only when force is set to true for input request.
html_to_pdf
Convert HTML to PDF. Ref: https://developer.pdf.co/api/pdf-from-html/convert.md
The header and footer parameters can contain valid HTML markup with the following classes used to inject printing values into them:
- date: formatted print date
- title: document title
- url: document location
- pageNumber: current page number
- totalPages: total pages in the document
- img: tag is supported in both the header and footer parameter, provided that the src attribute is specified as a base64-encoded string.
For example, the following markup will generate Page N of NN page numbering:
<span style='font-size:10px'>Page <span class='pageNumber'></span> of <span class='totalPages'></span>.</span>image_to_pdf
Convert various image formats (JPG, PNG, TIFF) to PDF. Ref: https://developer.pdf.co/api/pdf-from-image.md
pdf_add_annotations_images_fields
Add text, images, forms, other PDFs, fill forms, links to external sites and external PDF files. You can update or modify PDF and scanned PDF files.
This tool supports three main ways to add content:
- annotations: Add text, links, shapes, etc. Properties: text, x, y, size, pages, color, link, fontName, fontItalic, fontBold, fontStrikeout, fontUnderline
- images: Add images or other PDF content Properties: url, x, y, width, height, pages
- fields: Fill existing form fields Properties: fieldName, pages, text, fontName, size, fontBold, fontItalic, fontStrikeout, fontUnderline
Example annotations: [{"text": "Sample Text - Click here to test link", "x": 250, "y": 240, "size": 24, "pages": "0-", "color": "CCBBAA", "link": "https://pdf.co/", "fontName": "Comic Sans MS", "fontItalic": true, "fontBold": true, "fontStrikeout": false, "fontUnderline": true}]
Example images: [{"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-edit/logo.png", "x": 270, "y": 150, "width": 159, "height": 43, "pages": "0"}]
Example fields: [{"fieldName": "topmostSubform[0].Page1[0].YourSocial_ReadOrderControl[0].f1_05[0]", "pages": "1", "text": "Joan B.", "fontName": "Arial", "size": 6, "fontBold": true, "fontItalic": true, "fontStrikeout": true, "fontUnderline": true}]
Ref: https://developer.pdf.co/api/pdf-add.md
pdf_add_password
Add password protection to a PDF file. Ref: https://developer.pdf.co/api/pdf-password/add.md
pdf_info_reader
Get detailed information about a PDF document - number of pages, metadata, security, form fields, and more. Ref: https://developer.pdf.co/api/pdf-info-reader.md
pdf_make_searchable
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/pdf-change-text-searchable/searchable.md
pdf_make_unsearchable
Make existing PDF document non-searchable by removing the text layer from it. Ref: https://developer.pdf.co/api/pdf-change-text-searchable/unsearchable.md
pdf_merge
Merge PDF from two or more PDF, DOC, XLS, images, even ZIP with documents and images into a new PDF. Ref: https://developer.pdf.co/api/merge/various-files.md
pdf_remove_password
Remove password protection from a PDF file. Ref: https://developer.pdf.co/api/pdf-password/remove.md
pdf_split
Split a PDF into multiple PDF files using page indexes or page ranges. Ref: https://developer.pdf.co/api/pdf-split/by-pages.md
pdf_to_csv
Convert PDF and scanned images into CSV representation with layout, columns, rows, and tables. Ref: https://developer.pdf.co/api/pdf-to-csv.md
pdf_to_html
Convert PDF and scanned images to HTML format. Ref: https://developer.pdf.co/api/pdf-to-html.md
pdf_to_image
Convert PDF and scanned images to various image formats (JPG, PNG, WebP, TIFF). Ref:
- https://developer.pdf.co/api/pdf-to-image/jpg.md
- https://developer.pdf.co/api/pdf-to-image/png.md
- https://developer.pdf.co/api/pdf-to-image/webp.md
- https://developer.pdf.co/api/pdf-to-image/tiff.md
pdf_to_json
Convert PDF and scanned images into JSON representation with text, fonts, images, vectors, and formatting preserved using the /pdf/convert/to/json2 endpoint. Ref: https://developer.pdf.co/api/pdf-to-json/basic.md
pdf_to_text
Convert PDF and scanned images to text with layout preserved. Ref: https://developer.pdf.co/api/pdf-to-text/basic.md
pdf_to_xls
Convert PDF and scanned images to XLS (Excel 97-2003) format. Ref: https://developer.pdf.co/api/pdf-to-excel/xls.md
pdf_to_xlsx
Convert PDF and scanned images to XLSX (Excel 2007+) format. Ref: https://developer.pdf.co/api/pdf-to-excel/xlsx.md
pdf_to_xml
Convert PDF and scanned images to XML format. Ref: https://developer.pdf.co/api/pdf-to-xml.md
read_pdf_forms_info
Extracts information about fillable PDF fields from an input PDF file. Ref: https://developer.pdf.co/api/forms/info-reader.md
upload_file
Upload a file to the PDF.co API
wait_job_completion
Wait for a job to complete
webpage_to_pdf
Convert external webpage URL to PDF. Ref: https://developer.pdf.co/api/pdf-from-url.md
The header and footer parameters can contain valid HTML markup with the following classes used to inject printing values into them:
- date: formatted print date
- title: document title
- url: document location
- pageNumber: current page number
- totalPages: total pages in the document
- img: tag is supported in both the header and footer parameter, provided that the src attribute is specified as a base64-encoded string.
For example, the following markup will generate Page N of NN page numbering:
<span style='font-size:10px'>Page <span class='pageNumber'></span> of <span class='totalPages'></span>.</span>BEFORE YOU INSTALL
What to know first
Tools you get
38 tools when we connected. The form-filling tool is called fill_forms, not fill_pdf_forms as documented. upload_file, get_job_check and wait_job_completion handle PDF.co's asynchronous jobs rather than PDF work.
Requires
- uvx on PATH
- X_API_KEY in your environment
Where it runs
Both documented clients run the server on your machine.
CONTEXT COST
Heavy Standing cost
Rated by the size of the 38 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx pdfco-mcpMCP Clients
Cursor, Claude Desktop
JSON
{
"mcpServers": {
"pdfco": {
"command": "uvx",
"args": [
"pdfco-mcp"
],
"env": {
"X_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
