pdf4me-mcp
OfficialThe PDF4me MCP server enables AI assistants to perform PDF, document, image, and barcode processing via the PDF4me API. Key capabilities include:
PDF Conversion: Convert PDFs to/from Word, Excel, PowerPoint, PDF/A, HTML, Markdown, Visio, and images; convert HTML/URL to PDF, JSON to Excel, and Word to fillable PDF forms.
PDF Editing & Modification: Add stamps/watermarks, headers/footers, page numbers, margins, hyperlinks, attachments, and signatures; find/replace text or images; flatten, repair, and linearize PDFs.
PDF Organization: Merge, overlay, split by pages, ranges, barcodes, Swiss QR, or text; delete/extract/rotate pages; remove blank pages.
PDF Extraction & Analysis: Extract form data, tables, text by regex, attachments, resources, metadata; classify documents; retrieve PDF/image metadata.
AI Document Processing: Extract structured data from invoices, receipts, bank statements, cheques, contracts, mortgage, tax, pay stubs, IDs, health/credit cards, marriage certificates, shipping labels, and universal documents.
Barcode & QR Code: Generate/read barcodes and QR codes, add to PDFs, split by barcode, create/read Swiss QR bills.
Image Processing: Convert formats, resize/rotate/flip/crop, compress, watermark, OCR text extraction, EXIF read/strip, auto-rotate; create images from PDFs.
Word & Document Tools: Enable/disable/extract tracked changes, replace text with images, extract text from Word.
Document Generation: Generate single/batch documents from templates with JSON/XML/text data.
Security: Protect/unlock PDFs with passwords and permissions; create ZUGFeRD e-invoices.
Utilities: Upload files to cloud storage, repair PDFs, optimize (compress/linearize/flatten), register webhooks to receive documents.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pdf4me-mcp Merge these two PDFs into one document"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
PDF4me MCP Server
PDF4me MCP Server provides PDF4me API functionality through the Model Context Protocol (MCP), enabling AI assistants to easily perform a wide range of PDF, document, image, and barcode processing tasks.
π Key Features
π PDF Conversion
PDF β Office: Convert PDFs to Word (DOCX), Excel (XLSX), PowerPoint (PPTX)
PDF β Other Formats: Convert PDFs to PDF/A, searchable OCR PDF, HTML, Markdown
Office β PDF: Convert DOCX, PPTX, XLSX, CSV, HTML, Markdown, Visio, and images to PDF
Word β PDF Form: Convert Word documents into fillable PDF forms
JSON β Excel: Convert JSON data files into Excel workbooks
π οΈ PDF Editing & Modification
Stamps & Watermarks: Add text or image stamps/watermarks to PDFs
Headers & Footers: Inject HTML-based headers and footers
Annotations: Add page numbers, margins, hyperlink annotations
Attachments: Embed any file as an attachment inside a PDF
Signing: Apply signature images to PDF pages
Find & Replace: Search and replace text, or replace text with images
π PDF Organization
Merge: Combine multiple PDFs or overlay two PDFs
Split: Split by page, page range, barcode, Swiss QR code, or matching text
Delete / Extract: Remove or extract specific pages, delete blank pages
Rotate: Rotate all pages or selected pages of a PDF
π PDF Extraction & Analysis
Form Data: Extract values from fillable PDF form fields
Tables: Detect and extract tables with coordinates
Text: Extract text by regex expression; find and replace text
Attachments: Pull embedded file attachments out of a PDF
Resources: Extract text and images from PDF content
Classification: Classify a PDF by document type, category, and confidence
π€ AI Document Processing
Invoices, Orders, Receipts: Structured data extraction using AI
Bank Statements & Cheques: Parse financial documents automatically
Contracts & Mortgage Documents: Extract key fields from legal documents
Tax Documents & Pay Stubs: Parse tax forms and payroll documents
ID & Cards: Process health cards, credit cards, marriage certificates, and shipping labels
Universal Extraction: Generic AI data extraction from any document type
π·οΈ Barcode & QR Codes
Create: Generate barcodes and QR codes (PNG)
Add to PDF: Stamp a barcode or QR code onto PDF pages
Read from PDF / Image: Detect and decode barcodes and QR codes
Swiss QR Bill: Create and read Swiss QR Bill payment sections; split PDFs by Swiss QR
πΌοΈ Image Processing
Format Conversion: Convert between BMP, GIF, JPG, PNG, TIFF
Editing: Resize, rotate, flip, and crop images
Watermarks: Add image or text watermarks to images
OCR: Extract text from images using OCR
Metadata: Read or strip EXIF metadata
Compression: Compress images with configurable quality levels
π Word & Document Tools
Track Changes: Enable, disable, or extract tracked changes in Word documents
Replace Text with Image: Substitute text placeholders with images in Word
Extract Text: Pull text from Word documents with header/footer and comment control
π¦ Document Generation
Single Document: Generate one document from a template and data (JSON, XML, or plain text)
Batch Documents: Generate multiple documents from a single template and dataset
π Security
Protect PDF: Apply password protection with configurable permissions
Unlock PDF: Remove password protection from a PDF
ZUGFeRD Invoice: Create standards-compliant ZUGFeRD e-invoices (XML or PDF+XML)
βοΈ Utilities
Upload File: Upload local files to PDF4me cloud storage
PDF Metadata: Read full metadata (title, author, page count, security info, dates)
Image Metadata: Read image properties and EXIF fields
Repair PDF: Repair corrupted or malformed PDFs
Optimize PDF: Compress, linearize (web-optimize), or flatten PDFs
Related MCP server: PDF Manipulation MCP Server
βοΈ Configuration
π Get API Key
Sign up at dev.pdf4me.com
Get your API key from the dashboard
π¦ Install UV
You need UV (a fast Python packaging tool) to run this MCP server.
macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | shWindows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Alternative methods
# Homebrew (macOS)
brew install uv
# pipx
pipx install uv
# pip
pip install uvFor more options, see the UV installation guide.
π§ MCP Client Setup
Cursor
Open Cursor Settings β MCP, or edit ~/.cursor/mcp.json (macOS/Linux) / %USERPROFILE%\.cursor\mcp.json (Windows):
{
"mcpServers": {
"pdf4me-mcp": {
"command": "uvx",
"args": ["pdf4me-mcp"],
"env": {
"PDF4ME_API_KEY": "your-api-key-here"
}
}
}
}Claude Desktop
Open the Claude Desktop config file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"pdf4me-mcp": {
"command": "uvx",
"args": ["pdf4me-mcp"],
"env": {
"PDF4ME_API_KEY": "your-api-key-here"
}
}
}
}VS Code
Open ~/.config/Code/User/mcp.json (macOS/Linux) or %APPDATA%\Code\User\mcp.json (Windows):
{
"servers": {
"pdf4me-mcp": {
"type": "stdio",
"command": "uvx",
"args": ["pdf4me-mcp"],
"env": {
"PDF4ME_API_KEY": "your-api-key-here"
}
}
}
}Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"pdf4me-mcp": {
"command": "uvx",
"args": ["pdf4me-mcp"],
"env": {
"PDF4ME_API_KEY": "your-api-key-here"
}
}
}
}Continue (VS Code / JetBrains extension)
Add to your ~/.continue/config.json:
{
"mcpServers": [
{
"name": "pdf4me-mcp",
"command": "uvx",
"args": ["pdf4me-mcp"],
"env": {
"PDF4ME_API_KEY": "your-api-key-here"
}
}
]
}πͺ Windows Note
On Windows, uvx may need to be called with its full path if it is not on your PATH. Replace "command": "uvx" with the full path, e.g.:
"command": "C:\\Users\\<YourUser>\\.local\\bin\\uvx"π οΈ Available Tools
π·οΈ Barcode Tools
Tool | Description |
| Draw a barcode or QR code onto PDF pages with configurable alignment and size |
| Generate a barcode or QR code as a PNG image (supports Code128, QR, and more) |
| Read and decode barcode/QR data from a local PDF with barcode type and page filtering |
| Detect and decode barcodes and QR codes from a local image file |
| Add a Swiss QR Bill payment section to a PDF (IBAN, creditor details, currency, reference) |
| Parse and extract Swiss QR Bill payment data from a local PDF |
| Split a PDF into multiple files at pages that contain a specific barcode value or type |
| Split a PDF by Swiss QR code positions into separate PDF files or a ZIP archive |
π Conversion Tools
Tool | Description |
| Convert documents (DOCX, PPTX, XLSX, images, text formats) to PDF |
| Convert a local HTML file to PDF with layout, margins, and print options |
| Convert a web page URL to PDF with auth, layout, and margin settings |
| Convert a local Markdown file to PDF |
| Convert a Visio file (.vsdx/.vsd/.vsdm) to PDF |
| Convert a Word document (DOCX) into a fillable PDF form |
| Convert a PDF to DOCX with quality settings, language, and optional OCR |
| Convert a PDF to XLSX with quality, merge sheets, language, and optional OCR |
| Convert a PDF to PPTX with quality, language, and optional OCR |
| Convert a PDF to PDF/A (PdfA1a through PdfA3u) with upgrade/downgrade control |
| Make a scanned PDF searchable by running OCR and embedding a text layer |
| Convert a local JSON file to an Excel workbook (XLSX) with worksheet name and title options |
| Convert images between BMP, GIF, JPG, PNG, and TIFF formats |
| Flatten a PDF (merge form fields and annotations into the page content) |
| Linearize (web-optimize) a PDF for fast browser loading with configurable optimization presets |
βοΈ PDF Editing Tools
Tool | Description |
| Embed one or more files as attachments inside a PDF |
| Add an HTML-formatted header, footer, or both to PDF pages |
| Add page margins (in millimeters) to all pages of a PDF |
| Insert page numbers with configurable alignment, format, and font styling |
| Place an image stamp or watermark on PDF pages with alignment, opacity, and size controls |
| Place a text stamp or watermark on PDF pages with font, opacity, rotation, and alignment options |
| Apply a signature image to a PDF with layout and margin options |
| Find and replace text across PDF pages |
| Replace text occurrences in a PDF with an image at configurable dimensions |
| Update or replace hyperlink annotations in a PDF by search criteria |
| Repair a corrupted or malformed PDF file |
π€ Extract Tools
Tool | Description |
| Extract specific pages from a PDF into a new PDF file |
| Extract all form field names and their current values from a PDF |
| Extract embedded file attachments from a PDF and save them to disk |
| Extract text content and images embedded in a PDF |
| Detect and extract tables from a PDF, saving results as JSON and CSV |
| Extract text from a PDF using a regular expression pattern |
| Extract text from a Word document, with options to remove headers, footers, or comments |
| Extract text from an image using OCR |
| Classify a PDF by document type and category with a confidence score |
| Extract structured data from a PDF using a predefined PDF4me parsing template |
π Forms Tools
Tool | Description |
| Add new TextBox or CheckBox form fields to a PDF at specified coordinates |
| Fill existing form fields in a PDF using a key/value data map |
π Document Generation Tools
Tool | Description |
| Generate one document from a template (DOCX/HTML/PDF) and a data payload (JSON/XML/text) |
| Generate multiple documents in batch from one template and a multi-record dataset |
| Enable Track Changes mode in a Word document |
| Disable Track Changes mode in a Word document |
| Extract all tracked change data from a Word document as structured JSON |
| Replace text placeholders in a Word document with an image |
πΌοΈ Image Tools
Tool | Description |
| Overlay a watermark image onto another image with opacity and position controls |
| Add a text watermark to an image with font, color, opacity, and rotation options |
| Compress a JPG, PNG, or WebP image with configurable compression level |
| Convert an image between BMP, GIF, JPG, PNG, and TIFF formats |
| Render PDF pages to image files (JPEG, PNG, TIFF) with page selection and width options |
| Crop an image by border or by a specific rectangle region |
| Flip an image horizontally or vertically |
| Extract image properties and EXIF metadata from a JPG or PNG file |
| Run OCR on an image to extract its text content |
| Resize an image by percentage or to specific dimensions, with aspect ratio control |
| Rotate an image by a specified angle with background color and resize options |
| Auto-rotate an image to its correct orientation based on its EXIF metadata |
| Strip all EXIF metadata from a JPG or PNG image |
π Merge & Split Tools
Tool | Description |
| Merge two or more PDF files into a single PDF |
| Overlay one PDF on top of another (e.g. stamp a letterhead) |
| Split a PDF by page number, recurring interval, sequence, or page ranges |
| Split a PDF at pages containing a specified barcode |
| Split a PDF at Swiss QR code positions |
| Split a PDF at pages containing a specific text string |
β‘ Optimize Tools
Tool | Description |
| Compress a PDF with optimization profiles for Web, Print, or Screen |
| Remove blank pages from a PDF (no text, no images, or both) |
| Linearize a PDF for fast incremental loading in web browsers |
π Organize Tools
Tool | Description |
| Remove specific pages from a PDF by page number or range |
| Extract selected pages from a PDF into a new file |
| Rotate all pages of a PDF (Clockwise, CounterClockwise, UpsideDown) |
| Rotate selected pages of a PDF independently |
π PDF Information Tools
Tool | Description |
| Read full PDF metadata: title, author, page count, security info, and dates |
| Read image properties and available EXIF fields from a JPG or PNG |
| Attempt to repair a corrupted or malformed PDF |
π Security Tools
Tool | Description |
| Password-protect a PDF with configurable permissions (print, copy, edit, etc.) |
| Remove password protection from a PDF using the current password |
π€ AI Document Processing Tools
Tool | Description |
| Extract structured invoice data (line items, totals, dates, vendor info) from a PDF or image using AI |
| Parse bank cheque images and extract cheque details using AI |
| Extract key clauses and fields from contract documents using AI |
| Extract credit card information from card images using AI |
| Extract data from health insurance card images using AI |
| Extract fields from marriage certificates using AI, with optional authenticity verification |
| Extract key financial and property details from mortgage documents using AI |
| Extract earnings, deductions, and employee details from pay stub documents using AI |
| Parse bank statements for transactions, balances, and patterns using AI |
| Extract order details (items, quantities, prices, addresses) from purchase order documents using AI |
| Extract merchant info, line items, and totals from receipt images or PDFs using AI |
| Extract carrier, tracking number, and address data from shipping labels using AI |
| Extract tax form fields and computed values from tax documents using AI |
| Extract any specified fields from any document type using AI (configurable field list) |
π ZUGFeRD / E-Invoice Tools
Tool | Description |
| Create a ZUGFeRD-compliant e-invoice from XML, JSON, or CSV data β as PDF+XML or XML-only |
ποΈ File Management Tools
Tool | Description |
| Upload a local file to PDF4me cloud storage and receive a file reference for further operations |
| Register a webhook callback URL to receive documents from PDF4me |
π‘ Usage Examples
Convert a PDF to Word:
Convert this PDF to a Word document: /path/to/document.pdfMerge multiple PDFs:
Merge these PDFs into one: report.pdf, appendix.pdf, cover.pdfExtract invoice data using AI:
Extract all invoice details from this file: invoice.pdfAdd a Swiss QR Bill to a PDF:
Add a Swiss QR Bill to invoice.pdf with IBAN CH93-0076-2011-6238-5295-7, creditor name "Acme AG"Split a PDF by barcode:
Split this PDF at every page containing a Code128 barcode: batch.pdfGenerate a document from a template:
Generate a contract PDF from contract_template.docx with this data: {"client": "ACME", "date": "2024-01-01"}Compress an image:
Compress this PNG image with maximum compression: photo.pngOCR a scanned PDF:
Make this scanned PDF searchable: scanned_report.pdfπ οΈ Manual Run (without a client)
uvx pdf4me-mcpOr, if installed locally:
PDF4ME_API_KEY=your-api-key-here pdf4me-mcpπ Support & Contact
PDF4me: pdf4me.com
API Documentation: docs.pdf4me.com
Issue Reports: GitHub Issues
π License
This project is distributed under the MIT License.
Available Tools
92 toolsadd_attachment_to_pdfAInspect
Embed one or more files as attachments into a PDF using the PDF4me AddAttachmentToPdf API. Provide the path to the source PDF and a list of local file paths to attach (docName is each file's basename). Optional: request_doc_name for the API docName field (defaults to the PDF's filename) and output path.
Inputs: pdf_file_path (required), attachment_file_paths (required), output_dir, output_file_name, +1 more.
add_barcode_to_pdfAInspect
Draw a barcode or QR code onto PDF pages using the PDF4me addbarcode API (/api/v2/addbarcode). Requires local pdf_file_path, barcode text, barcodeType (e.g. qrCode, code128), pages spec (e.g. all, 1, 1-3, 1,3,5), alignX (Left/Center/Right), alignY (Top/Middle/Bottom), hideText. Optional: size/margins in MM or points, opacity, displayText, showOnlyInPrint, isTextAbove.
Inputs: text (required), pdf_file_path (required), pages, align_x, +18 more.
add_form_fields_to_pdfAInspect
Add an interactive form field (TextBox or CheckBox) to a PDF via PDF4me AddFormField (/api/v2/AddFormField). Provide the PDF path, field name, initial value, position (X/Y in PDF units), Size, pages spec, and formFieldType. Saves the resulting PDF to disk.
Inputs: size (required), pages (required), field_name (required), position_x (required), +7 more.
add_image_stamp_to_pdfBInspect
Stamp or watermark a PDF with an image using PDF4me ImageStamp (/api/v2/ImageStamp). Provide pdf_file_path, image_file_path (PNG/JPG/etc.), alignX (Left/Center/Right), alignY (Top/Middle/Bottom). Optional: pages, size in MM or pixels, margins, opacity, is_background, show_only_in_print, output path.
Inputs: align_x (required), align_y (required), pdf_file_path (required), image_file_path (required), +16 more.
add_image_watermark_to_imageAInspect
Overlay a watermark image on a source image via PDF4me AddImageWatermarkToImage (/api/v2/AddImageWatermarkToImage). Provide image_file_path, watermark_image_file_path, and position (topright, topleft, bottomright, bottomleft, centralhorizontal, diagonal, centralvertical, custom). Optional: opacity (0.0β1.0), horizontal/vertical offset, position_x/y for custom, rotation (degrees), output path.
Inputs: position (required), image_file_path (required), watermark_image_file_path (required), opacity, +9 more.
add_margin_to_pdfAInspect
Add margins to a PDF using the PDF4me AddMargin API. Provide a local PDF path and optional margins in millimeters (margin_left/right/top/bottom, 0-100). Saves the resulting PDF to disk.
Inputs: pdf_file_path (required), margin_top, output_dir, margin_left, +4 more.
add_page_number_to_pdfAInspect
Add page numbers to a PDF via PDF4me POST /api/v2/AddPageNumber. When helping a user, explain how to set page_number_format before calling: use the literal character # for the current page (1, 2, 3, β¦) and the literal substring {1} for the total page count. Those are placeholders, not Python format specifiersβpass them exactly as strings (e.g. '# of {1}' renders as '1 of 10', 'Page #' as 'Page 1', '# / {1}' as '1 / 10', '(#)' as '(1)', '#' alone as '1'). align_x must be left, center, or right; align_y must be top, middle, or bottom. Optional: margin_x_in_mm and margin_y_in_mm (integers 0β100 mm from the chosen edge), font_size (8β72), is_bold, is_italic, skip_first_page. Requires a local pdf_file_path; output defaults next to the source file.
Inputs: pdf_file_path (required), page_number_format (required), align_x, align_y, +9 more.
add_text_stamp_to_pdfAInspect
Add a text stamp or watermark to a PDF using PDF4me Text Stamp (/api/v2/Stamp). Provide pdf_file_path, stamp text, pages (e.g. all, 1, 1-3), alignX/alignY, font and margin settings. Uses API field isItalics (italic). Saves the stamped PDF to disk.
Inputs: text (required), pdf_file_path (required), pages, rotate, +20 more.
add_text_watermark_to_imageBInspect
Add a text watermark to an image via PDF4me AddTextWatermarkToImage (/api/v2/AddTextWatermarkToImage). image_file_path, watermark_text, text_position (e.g. bottomleft, diagonal, custom), text_font_family, is_underline, is_italic; optional font size, colour, bold, opacity, rotation, position_x/y.
Inputs: text_position (required), watermark_text (required), image_file_path (required), is_bold, +12 more.
classify_documentBInspect
Classify a PDF by content via PDF4me ClassifyDocument (/api/v2/ClassifyDocument). pdf_file_path; optional request_doc_name and output_dir. Saves classified_document.json.
Inputs: pdf_file_path (required), output_dir, request_doc_name.
compress_imageAInspect
Compress an image via PDF4me CompressImage (/api/v2/CompressImage). image_file_path, image_type (JPG, PNG, WebP), compression_level (Max, Medium, Low); optional doc_name, output_dir, output_file_name. Uses async 202 polling when applicable.
Inputs: image_file_path (required), doc_name, image_type, output_dir, +2 more.
compress_pdfAInspect
Compress a PDF file using the PDF4me API to reduce file size. Provide the local file path to the PDF. Choose an optimization profile: Web (fast download), Print (high-quality), or Screen (screen viewing). Optionally specify an output directory and output file name.
Inputs: file_path (required), output_dir, optimize_profile, output_file_name.
convert_html_to_pdfAInspect
Convert a local HTML file to PDF using the PDF4me ConvertHtmlToPdf API. Provide the file path to the HTML document. Configure layout, page format, scale, margins, print background, and header/footer. Optionally set output directory and output file name.
Inputs: file_path (required), scale, layout, output_dir, +8 more.
convert_image_formatAInspect
Convert a local image between formats (BMP, GIF, JPG, PNG, TIFF) using the PDF4me ConvertImageFormat API. Provide the local image path plus current and new format. Supports sync/async processing and optional output directory and output file name.
Inputs: file_path (required), output_dir, new_image_format, output_file_name, +1 more.
convert_json_to_excelAInspect
Convert a local JSON file to Excel (XLSX) using the PDF4me ConvertJsonToExcel API. Provide the file path to UTF-8 JSON. Options: worksheet_name, title formatting, number/date conversion and formats, ignore_null_values, first_row/first_column (1-based), and optional output path.
Inputs: file_path (required), first_row, output_dir, date_format, +8 more.
convert_md_to_pdfAInspect
Convert a local Markdown file (.md) to PDF using the PDF4me ConvertMdToPdf API. Provide the file path to the Markdown file and output_dir where the PDF will be saved. Long HTTP timeouts on requests. complete. Optional output file name (defaults to <input_basename>.pdf).
Inputs: file_path (required), output_dir (required), output_file_name.
convert_ocr_pdfAInspect
Convert a PDF to a searchable, editable PDF using the PDF4me ConvertOcrPdf API (OCR). Provide the local path to the input PDF, quality (Draft or High), ocr_when_needed, and language (e.g. eng). The API request body only includes docContent, docName, qualityType, ocrWhenNeeded, and language. If the API returns 202, the tool polls the Location URL until the PDF is ready. Optional output directory and output file name.
Inputs: file_path (required), language, output_dir, quality_type, +2 more.
convert_pdf_to_excelAInspect
Convert a local PDF file to Excel (XLSX) using the PDF4me ConvertPdfToExcel API. Provide the file path to the PDF. Options: quality (Draft/High), merge_all_sheets, language, OCR when needed, and optional output path. Output is always XLSX.
Inputs: file_path (required), language, output_dir, quality_type, +3 more.
convert_pdf_to_pdfaAInspect
Convert a PDF file to PDF/A (archival ISO format) using the PDF4me PdfA API. Provide the local file path to the PDF. Choose compliance (e.g. PdfA1b), allow_upgrade / allow_downgrade, and optional output path.
Inputs: file_path (required), compliance, output_dir, allow_upgrade, +2 more.
convert_pdf_to_powerpointAInspect
Convert a local PDF file to PowerPoint (PPTX) using the PDF4me ConvertPdfToPowerPoint API. Provide the file path to the PDF. Options: quality (Draft/High), language, OCR when needed, merge_all_sheets, and optional output path. Output is always PPTX.
Inputs: file_path (required), language, output_dir, quality_type, +3 more.
convert_pdf_to_wordAInspect
Convert a local PDF file to Word (DOCX) using the PDF4me ConvertPdfToWord API. Provide the file path to the PDF. Options: quality (Draft/High), merge_all_sheets, language, OCR when needed, and optional output path. Output is always DOCX.
Inputs: file_path (required), language, output_dir, quality_type, +3 more.
convert_to_pdfAInspect
Convert a local document file (for example DOCX, PPTX, XLSX, images, or text formats) to PDF using the PDF4me ConvertToPdf API. Provide the local file path, plus optional output directory and output file name.
Inputs: file_path (required), output_dir, output_file_name.
convert_url_to_pdfAInspect
Convert a web page to PDF using the PDF4me ConvertUrlToPdf API. Required input is only web_url (https://...); no local file path is read. Optional: layout, page format, margins, scale, print background, auth (NoAuth or credentials), output_dir/output_file_name for where to save the PDF (default file name output.pdf).
Inputs: web_url (required), scale, layout, password, +11 more.
convert_visio_to_pdfBInspect
Convert a local Visio file (.vsdx/.vsd/.vsdm) to PDF using the PDF4me ConvertVisio API. Supports PDF options (compliance, page range, hidden pages, foreground/toolbar, auto-fit), sync/async processing, and optional output directory/file name.
Inputs: file_path (required), auto_fit, output_dir, page_count, +6 more.
convert_word_to_pdf_formBInspect
Convert a local Word document (DOCX) to a PDF form with fillable fields using the PDF4me ConvertWordToPdfForm API. Provide the file path to the DOCX file. Optionally specify async polling and output directory/file name.
Inputs: file_path (required), output_dir, output_file_name.
create_barcodeAInspect
Create a standalone barcode or QR code image (PNG) using the PDF4me Create Barcode API. Pass the text to encode and barcodeType (e.g. qrCode, code128, dataMatrix, ean13, upcA). hideText hides the human-readable label. Saves the file and returns the path.
Inputs: text (required), hide_text, output_dir, barcode_type, +1 more.
create_images_from_pdfAInspect
Render PDF pages to image files using the PDF4me CreateImages API (POST /api/v2/CreateImages). Controls width in pixels, image format (jpeg, png, tiff, etc.), and page selection (top-level pageNrs plus imageAction.PageSelection.PageNrs when the expression parses to integers; use 'all' for all pages). Writes one file per page to output_dir (defaults to the input PDF directory).
Inputs: file_path (required), output_dir, page_number, width_pixel, +1 more.
create_swiss_qr_billAInspect
Create the Swiss QR bill payment part on a PDF using the PDF4me CreateSwissQrBill API (POST /api/v2/CreateSwissQrBill). Required inputs per OpenAPI: docContent, document.Name, iban, crName, crAddressType. Enums match backend: address S|K; currency CHF|EUR; language German|French|Italian|English; referenceType QRR|SCOR|NON; seperatorLine LineWithScissor|Line|None (string None). All other schema fields are optional (amount, creditor/debtor address lines, reference, etc.). Reads the source PDF from pdf_file_path (docContent base64); optional document_name overrides document.Name (defaults to the file basename). Output PDF name is output_file_name if set, otherwise 'swiss_qr_bill.pdf'. Saves next to the PDF unless output_dir is set; optional isAsync / 202 polling.
Inputs: iban (required), cr_name (required), pdf_file_path (required), amount, +23 more.
create_zugferd_invoiceAInspect
Create a ZUGFeRD e-invoice using PDF4me CreateZugferdInvoice API (POST /api/v2/CreateZugferdInvoice). Supports inputFormat XML/JSON/CSV, outputMode XmlWithPdf or XmlOnly, conformance level, and language. For XmlWithPdf, provide source PDF via source_pdf_path (docContent/document.Name are derived from the file). Saves output as PDF or XML and returns output metadata.
Inputs: language, output_dir, output_mode, input_format, +8 more.
crop_imageAInspect
Crop an image via PDF4me CropImage (/api/v2/CropImage). Choose crop_type Border or Rectangle. Border: set left/right/top/bottom border in pixels. Rectangle: set upper_left_x/y and width/height.
Inputs: image_file_path (required), width, height, doc_name, +9 more.
delete_blank_pages_from_pdfCInspect
Delete blank pages from a PDF via PDF4me DeleteBlankPages (/api/v2/DeleteBlankPages). Provide pdf_file_path and delete_page_option (NoTextNoImages, NoText, NoImages). Saves cleaned PDF to disk.
Inputs: pdf_file_path (required), output_dir, output_file_name, request_doc_name, +1 more.
delete_pdf_pagesBInspect
Remove pages from a PDF using the PDF4me DeletePages API. Provide the local PDF path and pageNumbers (e.g. '2', '1,3,5', or '2-4'). Optionally set output directory and output file name.
Inputs: file_path (required), page_numbers (required), output_dir, output_file_name.
disable_tracking_changes_in_wordDisable Track Changes in WordAInspect
Disable Word Track Changes via PDF4me /api/v2/DisableTrackingChangesInWord. Input is a local Word file path (.docx or .doc) which is sent as docContent Base64; docName defaults to the input filename. Saves a Word output file with track changes disabled.
Inputs: word_file_path (required), output_dir, output_file_name, request_doc_name.
enable_tracking_changes_in_wordEnable Track Changes in WordAInspect
Enable Word Track Changes via PDF4me /api/v2/EnableTrackingChangesInWord. Input is a local Word file path (.docx or .doc) which is sent as docContent Base64; docName defaults to the input filename. Saves a Word output file with track changes enabled.
Inputs: word_file_path (required), output_dir, output_file_name, request_doc_name.
extract_attachment_from_pdfAInspect
Extract embedded file attachments from a PDF via PDF4me ExtractAttachmentFromPdf (/api/v2/ExtractAttachmentFromPdf). pdf_file_path; optional output_dir (defaults next to PDF). Saves extracted_attachments.json when JSON, decodes outputDocuments to files, or saves/extracts ZIP.
Inputs: pdf_file_path (required), output_dir, request_doc_name.
extract_form_data_from_pdfExtract Form Data From PDFAInspect
Extract all PDF form fields and values via PDF4me /api/v2/ExtractPdfFormData. Input is pdf_file_path; optional request_doc_name and output_dir. Saves extracted_form_data.json with the full API response.
Inputs: pdf_file_path (required), output_dir, request_doc_name.
extract_pages_from_pdfExtract Pages From PDFAInspect
Extract selected pages from a PDF via PDF4me /api/v2/Extract. Inputs: pdf_file_path and page_numbers (e.g. '1,3,5' or '1-5,10'). Optional request_doc_name and output path settings.
Inputs: pdf_file_path (required), output_dir, page_numbers, output_file_name, +1 more.
extract_resourcesAInspect
Extract text and/or embedded images from a PDF via PDF4me ExtractResources (/api/v2/ExtractResources). pdf_file_path, extract_text, extract_images; optional output_dir (defaults next to PDF). Writes extracted_resources.json, extracted_text.txt when text is extracted, and image files.
Inputs: pdf_file_path (required), output_dir, extract_text, extract_images, +1 more.
extract_table_from_pdfAInspect
Extract tables from a PDF via PDF4me ExtractTableFromPdf (/api/v2/ExtractTableFromPdf). pdf_file_path; optional output_dir (defaults next to PDF). Saves extracted_tables.json, per-table table_N.json, and table_N.csv when rows are available.
Inputs: pdf_file_path (required), output_dir, request_doc_name.
extract_text_by_expressionAInspect
Extract text from a PDF matching a regex via PDF4me ExtractTextByExpression (/api/v2/ExtractTextByExpression). pdf_file_path, expression, page_sequence (e.g. '1-' all pages, '1-3', '1,2,3'); optional output_dir. Saves JSON, a matches text file, and CSV.
Inputs: expression (required), pdf_file_path (required), output_dir, page_sequence, +1 more.
extract_text_from_imageAInspect
Extract text from a local image using the PDF4me ImageExtractText API (POST /api/v2/ImageExtractText). Uses OCR; supports async processing with polling on 202. Returns the parsed JSON response in structured_content and a text summary when possible.
Inputs: file_path (required).
extract_text_from_wordExtract Text from WordAInspect
Extract text from a Word document via PDF4me /api/v2/ExtractTextFromWord. Supports page range and content filtering options (comments, header/footer, tracked changes). Saves extracted text and JSON response metadata to disk.
Inputs: word_file_path (required), output_dir, accept_changes, end_page_number, +5 more.
fill_pdf_formBInspect
Fill form fields in a local PDF using the PDF4me FillPdfForm API. Provide the local PDF path and a JSON object of field/value pairs in form_data. Optionally specify output directory and output file name.
Inputs: file_path (required), form_data (required), output_dir, output_file_name.
find_and_replace_textFind And Replace TextCInspect
Find and replace text in a PDF via PDF4me /api/v2/FindAndReplace. Inputs: pdf_file_path, old_text, new_text, page_sequence; optional output path.
Inputs: new_text (required), old_text (required), pdf_file_path (required), output_dir, +3 more.
flatten_pdfAInspect
Flatten a PDF file with the PDF4me API: forms, annotations, and layers become static content. Provide the local file path to the PDF. Optionally specify an output directory and output file name.
Inputs: file_path (required), output_dir, output_file_name.
flip_imageFlip ImageAInspect
Flip an image horizontally or vertically via PDF4me /api/v2/FlipImage. Inputs: image_file_path and orientation ('horizontal' or 'vertical'); optional request_doc_name and output path.
Inputs: image_file_path (required), output_dir, orientation, output_file_name, +1 more.
generate_document_singleAInspect
Generate a single document from a template using PDF4me GenerateDocumentSingle API (POST /api/v2/GenerateDocumentSingle). Supports template file, document data text/file, output type, and async polling.
Inputs: output_dir (required), output_type (required), output_file_name (required), document_data_type (required), +7 more.
generate_documents_multipleAInspect
Generate multiple documents from one template and data using PDF4me GenerateDocumentMultiple API (POST /api/v2/GenerateDocumentMultiple). Supports async polling on 202; saves each output from outputDocuments[].streamFile.
Inputs: output_dir (required), output_type (required), output_file_name (required), document_data_type (required), +7 more.
get_document_from_pdf4meBInspect
Subscribe a callback webhook via PDF4me WebhookSubscribe (/api/v2/WebhookSubscribe). Provide callback_url and doc_name. Saves API response as JSON.
Inputs: doc_name (required), callback_url (required), output_dir, output_file_name.
get_image_metadataAInspect
Extract metadata from a local image using the PDF4me GetImageMetadata API. Provide the file path to a JPG or PNG image. Returns structured metadata JSON including image properties and available EXIF details.
Inputs: file_path (required), image_type.
get_pdf_metadataAInspect
Extract metadata from a local PDF using the PDF4me GetPdfMetadata API. Provide the file path to the PDF. Returns metadata such as title, author, page count, size, dates, and security properties.
Inputs: file_path (required).
get_tracking_changes_in_wordGet Tracking Changes In WordAInspect
Extract tracking changes data from a Word file via PDF4me /api/v2/GetTrackingChangesInWord. Input is a local .docx/.doc file. Saves the API response as JSON (or raw text fallback).
Inputs: word_file_path (required), output_dir, output_file_name, request_doc_name.
linearize_pdfAInspect
Linearize a PDF file with the PDF4me API for faster web loading and progressive display. Provide the local file path to the PDF. Choose optimize_profile: web, Max, Print, Default, WebMax, PrintMax, PrintGray, Compress, or CompressMax. Optionally specify an output directory and output file name.
Inputs: file_path (required), output_dir, optimize_profile, output_file_name.
merge_multiple_pdfsMerge Multiple PDFsCInspect
Merge multiple PDF files into one via PDF4me /api/v2/Merge. Inputs: pdf_file_paths (list of local PDFs), optional request_doc_name, and output path.
Inputs: pdf_file_paths (required), output_dir, output_file_name, request_doc_name.
merge_pdf_overlayMerge PDF OverlayBInspect
Overlay one PDF over another via PDF4me /api/v2/MergeOverlay. Inputs: base_pdf_file_path and overlay_pdf_file_path; optional output naming and async mode.
Inputs: base_pdf_file_path (required), overlay_pdf_file_path (required), output_dir, output_doc_name, +1 more.
parse_documentBInspect
Parse a PDF with a PDF4me parse template via ParseDocument (/api/v2/ParseDocument). Requires pdf_file_path, doc_name (or uses PDF basename), parse_id (or auto-generated UUID), and either template_id (GUID) or template_name. Saves parsed_document.json under output_dir.
Inputs: pdf_file_path (required), parse_id, output_dir, template_id, +2 more.
process_bank_chequeAI-Process Bank ChequeAInspect
AI-Process Bank Cheque: extract structured data from a bank cheque via PDF4me POST /api/v2/ProcessBankCheque (isAsync true: 202 + Location poll until JSON result). Request body uses isAsync (camelCase) and CustomFieldKeys (PascalCase) when custom keys are sentβnot the IsAsync/customFieldKeys shape used by AI-Invoice Parser. Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg as Base64). doc_name: logical file name (e.g. cheque.pdf); optional (defaults to basename). Optional custom_field_keys: include only as a non-empty list (property omitted when unused). Saves the full API JSON to process_bank_cheque.json.
Inputs: doc_name, output_dir, pdf_file_path, custom_field_keys.
process_bank_statementAI-Process Bank StatementAInspect
AI-Process Bank Statement (processBankStatement): extract structured data via PDF4me POST /api/v2/ProcessBankStatement. JSON uses camelCase isAsync (true), analyzePatterns (boolean, default true), and customFieldKeys (camelCase, not CustomFieldKeys)βomit customFieldKeys when there are no keys. Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg). doc_name is the logical docName sent to the API (optional: defaults to basename). Optional bank_name (omitted when empty). Optional custom_field_keys (list) and/or custom_field_keys_csv (comma-separated; trimmed, empty segments dropped)βmerged and deduped. Optional profiles string: trimmed empty omits the property; otherwise if it does not start with an opening curly brace or square bracket, the value is wrapped in outer curly braces for custom profiles. 202 + Location poll; saves process_bank_statement.json.
Inputs: doc_name, profiles, bank_name, output_dir, +4 more.
process_contractAI-Process ContractAInspect
AI-Process Contract: extract structured data from a contract via PDF4me POST /api/v2/ProcessContract. Request JSON has only docContent, docName, and IsAsync (must be true); this action does not send customFieldKeys or CustomFieldKeys. Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg as Base64). doc_name: logical file name (e.g. contract.pdf); optional (defaults to basename). Async: 202 + Location poll until JSON; saves process_contract.json.
Inputs: doc_name, output_dir, pdf_file_path.
process_credit_cardAI-Process Credit CardAInspect
AI-Process Credit Card: extract structured data from a credit card image/PDF via PDF4me POST /api/v2/ProcessCreditCard. Body uses IsAsync (must be true) and CustomFieldKeys (PascalCase) only when custom_field_keys is non-emptyβomit CustomFieldKeys when unused. Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg as Base64). doc_name optional (defaults to basename); names without an extension get .png (not .pdf). 202 + Location poll; saves process_credit_card.json.
Inputs: doc_name, output_dir, pdf_file_path, custom_field_keys.
process_health_cardAI-Process Health CardAInspect
AI-Process Health Card: extract structured data from a health card image/PDF via PDF4me POST /api/v2/ProcessHealthCard. Request JSON is only docContent, docName, and IsAsync (must be true); no customFieldKeys or CustomFieldKeys. Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg as Base64). doc_name optional (defaults to basename); names without an extension get .jpeg. 202 + Location poll; saves process_health_card.json.
Inputs: doc_name, output_dir, pdf_file_path.
process_invoiceAI-Invoice ParserAInspect
AI-Invoice Parser: extract structured invoice data from a document via PDF4me POST /api/v2/ProcessInvoice (async: 202 + Location poll until JSON result). Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg read as Base64). doc_name: logical document name for the API (e.g. invoice.pdf); optional (defaults to the file basename). Optional custom_field_keys: non-empty list of extra field names for the model to extract; omit the parameter when you have no custom keys (empty lists are not sent). Saves the full API JSON to process_invoice.json and returns key fields (invoiceNumber, vendorName, total, success, β¦).
Inputs: doc_name, output_dir, pdf_file_path, custom_field_keys.
process_marriage_certificateAI-Process Marriage CertificateAInspect
AI-Process Marriage Certificate: extract structured data via PDF4me POST /api/v2/ProcessMarriageCertificate. Base body: docContent, docName, IsAsync (true). VerifyAuthenticity is sent only when verify_authenticity is true (property omitted when false). CustomFieldKeys (PascalCase) is sent only when custom_field_keys is a non-empty list. Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg). doc_name optional (basename); names without an extension get .pdf. 202 + Location poll; saves process_marriage_certificate.json.
Inputs: doc_name, output_dir, pdf_file_path, custom_field_keys, +1 more.
process_mortgage_documentAI-Process Mortgage DocumentAInspect
AI-Process Mortgage Document: extract structured data via PDF4me POST /api/v2/ProcessMortgageDocument. Uses camelCase isAsync (true), not IsAsync. Body: docContent, docName, isAsync; optional documentType (hint, e.g. loanβomitted when empty); CustomFieldKeys (PascalCase) only when custom_field_keys is non-empty. Provide pdf_file_path (local .pdf only, must be a PDF file). doc_name optional (basename); 202 + Location poll; saves process_mortgage_document.json.
Inputs: doc_name, output_dir, document_type, pdf_file_path, +1 more.
process_orderAI-Process OrderAInspect
AI-Process Order (processOrder): extract structured order data via PDF4me POST /api/v2/ProcessOrder. JSON body: docName, docContent, isAsync (true), and optional profiles only. doc_name is sent as docName as provided or defaulted (basename from pdf_file_path)βnot overwritten by the server. Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg). Optional profiles: trim then omit if empty; otherwise if it does not start with an opening curly brace or square bracket, wrap in outer curly braces. 202 + Location poll; saves process_order.json.
Inputs: doc_name, profiles, output_dir, pdf_file_path.
process_pay_stubAI-Process Pay StubAInspect
AI-Process Pay Stub: extract structured data from a pay stub image/PDF via PDF4me POST /api/v2/ProcessPayStub. Body uses IsAsync (must be true) and CustomFieldKeys (PascalCase) only when custom_field_keys is non-emptyβomit CustomFieldKeys when unused. Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg as Base64). doc_name optional (defaults to basename); names without an extension get .png. 202 + Location poll; saves process_pay_stub.json.
Inputs: doc_name, output_dir, pdf_file_path, custom_field_keys.
process_receiptAI-Process ReceiptAInspect
AI-Process Receipt (processReceipt): extract structured receipt data via PDF4me POST /api/v2/ProcessReceipt. Body: docName, docContent, analyzeItems, extractMerchantInfo, calculateTotals (all booleans, defaults true), isAsync (true); optional receiptType (omit when empty or 'none'); customFieldKeys camelCase when keys present (list and/or CSV merged); optional profiles (sanitized like other process tools). Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg). docName resolution: uses basename unless doc_name is set. receipt_type examples: meal, supplies, hotel, fuel and energy, transportation, communication, subscriptions, entertainment, training, healthcare, generic. 202 + Location poll; saves process_receipt.json.
Inputs: doc_name, profiles, output_dir, receipt_type, +6 more.
process_shipping_labelAI-Process Shipping LabelAInspect
AI-Process Shipping Label (processShippingLabel): extract structured data via PDF4me POST /api/v2/ProcessShippingLabel. Body: docName (non-empty), docContent, isAsync (true), optional profiles. docName resolution: uses doc_name if set else the file basename. Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg). Optional profiles: trim, omit if empty; wrap in outer braces when not starting with an opening curly brace or square bracket. 202 + Location poll; saves process_shipping_label.json.
Inputs: doc_name, profiles, output_dir, pdf_file_path.
process_tax_documentAI-Process Tax DocumentAInspect
AI-Process Tax Document (processTaxDocument): extract structured tax data via PDF4me POST /api/v2/ProcessTaxDocument. Body: docName (sent exactly as doc_nameβtrimmedβor 'tax_document.pdf' if omitted; never replaced by local file basename or URL path in the request), docContent, isAsync (true); optional taxModel (omit when empty or 'none'); customFieldKeys camelCase when keys present (list and/or custom_field_keys_csv merged); optional profiles (sanitized). Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg). tax_model examples: W2, 1099, 1099-SSA, 1040, 1040-SR, 1040-NR, 1098, 1098-E, 1098-T, 1095A, 1095C, W-4, UnifiedTaxUS. 202 + Location poll; saves process_tax_document.json.
Inputs: doc_name, profiles, tax_model, output_dir, +3 more.
process_universal_documentAI - Universal Document Data ExtractionAInspect
AI - Universal Document Data Extraction (processUniversalDocument): extract named fields via PDF4me POST /api/v2/ProcessUniversalDocument. docName = file basename if available, else doc_name, else 'document.pdf'. fields (required): at least one field nameβuse fields and/or fields_csv (comma-separated, trimmed). mode: 0 Standard (default) or 1 Strict. isAsync true. Optional documentType (omit if empty); optional profiles (sanitized). Provide pdf_file_path (local .pdf/.png/.jpg/.jpeg). 202 + Location poll; saves process_universal_document.json.
Inputs: mode, fields, doc_name, profiles, +4 more.
protect_pdfAInspect
Password-protect a local PDF using the PDF4me Protect API. Provide the file path, open password, and pdf_permission (for example All). Optionally specify output directory and file name.
Inputs: password (required), file_path (required), output_dir, pdf_permission, +1 more.
read_barcodesAInspect
Read barcodes and QR codes from a local PDF using the PDF4me ReadBarcodes API. Provide the file path, barcode types (e.g. all, qrCode, dataMatrix, code128), and pages. Always requests async processing (isAsync true); on HTTP 202 the tool polls the Location URL. Returns structured barcode data as JSON.
Inputs: file_path (required), pages, barcode_type.
read_barcodes_from_imageAInspect
Read barcodes and QR codes from a local image using the PDF4me ReadBarcodesfromImage API. Provide the image path and optionally image type (JPG, PNG, GIF, BMP, TIFF, WEBP). (payload key isAsync). Returns structured barcode data as JSON.
Inputs: file_path (required), image_type.
read_swiss_qr_billAInspect
Read Swiss QR bill data from a local PDF using the PDF4me ReadSwissQRBill API. Provide the file path to the PDF. Returns structured Swiss QR data as JSON.
Inputs: file_path (required).
remove_exif_tags_from_imageAInspect
Remove EXIF metadata tags from a local image using the PDF4me RemoveEXIFTagsFromImage API. Supports sync and async processing with 202 polling. Uses long HTTP timeouts for large uploads and slow jobs. Input supports JPG/PNG; imageType is optional. output_file_name is required; output_dir is optional.
Inputs: file_path (required), output_file_name (required), image_type, output_dir.
repair_pdfAInspect
Repair a damaged or problematic PDF using the PDF4me RepairPdf API. Provide the local file path to the PDF. Optionally specify an output directory and output file name.
Inputs: file_path (required), output_dir, output_file_name.
replace_text_with_imageAInspect
Replace occurrences of a text string in a PDF with an image using the PDF4me ReplaceTextWithImage API (POST /api/v2/ReplaceTextWithImage). Provide the PDF path, image path, text to replace, page sequence (e.g. all, 1, 1,3,5, 2-5), and image width/height in pixels. Supports async via isAsync and 202 Location polling. Optional output directory and file name.
Inputs: file_path (required), replace_text (required), image_file_path (required), output_dir, +4 more.
replace_text_with_image_in_wordAInspect
Replace placeholder text in a Word document with an image using the PDF4me ReplaceTextWithImageInWord API (POST /api/v2/ReplaceTextWithImageInWord). Provide paths to the .docx/.doc file and image, SearchText to find, PageNumbers (e.g. 1 or 1,2), and optional first-page skip. Uses isAsync with 202 Location polling. Saves the modified Word file to disk.
Inputs: search_text (required), word_file_path (required), image_file_path (required), output_dir, +3 more.
resize_imageAInspect
Resize a local image using the PDF4me ResizeImage API (Percentage or Specific dimensions). Provide the image path, resize mode, and options (percentage or width/height, aspect ratio). Optional output directory and file name; saves the resized image to disk.
Inputs: file_path (required), width, height, output_dir, +4 more.
rotate_imageBInspect
Rotate a local image using the PDF4me RotateImage API. Supports rotation angle, background color, proportionate resize, and async 202 polling. Optional output directory and file name; saves the rotated image to disk.
Inputs: file_path (required), output_dir, rotation_angle, background_color, +2 more.
rotate_image_by_exif_dataAInspect
Automatically rotate a local image according to EXIF orientation metadata using the PDF4me RotateImageByExifData API. Supports async 202 polling. Requires output_dir; saves the rotated image under that directory.
Inputs: file_path (required), output_dir (required), output_file_name.
rotate_pdfAInspect
Rotate all pages of a PDF the same way using the PDF4me Rotate API. Provide the local PDF path and rotationType (NoRotation, Clockwise, CounterClockwise, UpsideDown). Optional output directory and file name.
Inputs: file_path (required), output_dir, rotation_type, output_file_name.
rotate_pdf_pageBInspect
Rotate selected pages of a PDF using the PDF4me RotatePage API. Provide the PDF path, page spec (e.g. "1", "1,3,5", "2-4"), and rotationType. Optional output directory and file name.
Inputs: page (required), file_path (required), output_dir, rotation_type, +1 more.
sign_pdfAInspect
Add a signature image to a PDF using the PDF4me SignPdf API. Provide paths to the PDF and signature image (e.g. JPG/PNG). Supports page ranges, alignment, size, margins, opacity, and async 202 polling. Optional output directory and file name; saves the signed PDF to disk.
Inputs: file_path (required), signature_file_path (required), pages, align_x, +14 more.
split_pdfCInspect
Split a PDF via PDF4me SplitPDF (/api/v2/SplitPdf). split_action supports RecurringSplitAfterPage, SplitAfterPage, SplitSequence, SplitRanges. Provide split_action_number for first two, split_sequence for SplitSequence, split_ranges for SplitRanges.
Inputs: split_action (required), pdf_file_path (required), output_dir, file_naming, +4 more.
split_pdf_by_barcodeBInspect
Split a PDF by barcode text via PDF4me SplitByBarcode (/api/v2/SplitByBarcode). Provide barcode_string, barcode_filter, barcode_type, split_barcode_page, combine_pages_with_same_consecutive_barcodes, and pdf_render_dpi.
Inputs: pdf_file_path (required), barcode_string (required), output_dir, barcode_type, +5 more.
split_pdf_by_swiss_qrCInspect
Split a PDF by Swiss QR via PDF4me SplitPdfByBarcode (/api/v2/SplitPdfByBarcode) (SplitDocBySwissQrCode). pdf_file_path, barcode_string (default SPC), barcode_filter, barcode_type, split_qr_page (before/after), pdf_render_dpi, combine_pages_with_same_barcodes (maps to combinePagesWithSameConsecutiveBarcodes).
Inputs: pdf_file_path (required), output_dir, barcode_type, split_qr_page, +5 more.
split_pdf_by_textBInspect
Split a PDF by matching text via PDF4me SplitByText (/api/v2/SplitByText). Provide pdf_file_path, text, split_text_page (before/after), and file_naming.
Inputs: text (required), pdf_file_path (required), output_dir, file_naming, +2 more.
unlock_pdfAInspect
Remove password protection from a local PDF using the PDF4me Unlock API. Provide the file path and the current open password. Optionally specify output directory and file name.
Inputs: password (required), file_path (required), output_dir, output_file_name.
update_hyperlink_annotationAInspect
Update hyperlink annotations in a PDF using PDF4me UpdateHyperlinkAnnotation API (POST /api/v2/UpdateHyperlinkAnnotation). Provide a local PDF path and all hyperlink update fields (SearchOn, SearchValue, IsExpression, TextCurrentValue, TextNewValue, URLCurrentValue, URLNewValue). Supports async via isAsync and 202 Location polling. Saves the updated PDF to disk.
Inputs: file_path (required), search_on (required), search_value (required), is_expression (required), +6 more.
upload_fileAInspect
Upload a local file to PDF4me storage using the UploadFile API (POST /api/v2/UploadFile). Sends payload with docName and docContent (base64). Returns the API response JSON/text (for example uploaded file reference details).
Inputs: file_path (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 92 tools
Many tools have overlapping purposes, especially the 14+ process_* AI extraction tools and the multiple split_pdf_by_* tools. For example, split_pdf_by_barcode and split_pdf_by_swiss_qr both split by barcode, and process_invoice vs process_receipt may be ambiguous for similar document types. Descriptions are detailed, but the sheer volume of similar tools makes misselection likely.
Tool names generally follow a consistent verb_noun pattern (add_*, convert_*, extract_*, process_*). Minor inconsistencies exist, such as merge_multiple_pdfs vs merge_pdf_overlay, and generate_document_single vs generate_documents_multiple, but overall naming is readable and predictable.
With 92 tools, the server is extremely overloaded. The typical well-scoped server has 3-15 tools; 92 is far beyond any reasonable threshold and will overwhelm agents. This extreme count likely leads to context bloat and decision paralysis.
The tool set covers a comprehensive range of PDF, image, conversion, and AI extraction operations, including create, read, update, delete, transform, and metadata operations. Minor gaps exist (e.g., no page reordering, no generic text editing beyond find-and-replace), but the coverage is broad and most common workflows are supported.
Related MCP Connectors
Convert, create and edit Word, PowerPoint, Excel and PDF documents from any AI agent.
Convert, merge, compress, OCR, redact, and sign PDFs inside your AI assistant. From pdfAssistant.
PDF tools for AI agents: validate, extract, merge, split, compress, OCR, sign and redact.
PDF tools: merge, split, compress, convert, OCR & more. OAuth with auto-registration or API key.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI-powered extraction and analysis of PDF documents with 40+ specialized tools for text, tables, images, layout analysis, security assessment, and document intelligence. Supports both text-based and scanned PDFs with OCR capabilities.216 PyPI11MIT
- AlicenseBqualityDmaintenanceEnables PDF manipulation including text, images, annotations, form fields, page operations, and metadata through natural language.16MIT
- AlicenseAqualityDmaintenanceEnables PDF processing and analysis including text extraction, metadata retrieval, search, page manipulation, splitting/merging, conversion to images, and form handling.10MIT
- AlicenseCqualityDmaintenanceEnables AI assistants to perform PDF operations like merge, split, compress, convert, encrypt, OCR, and summarize using natural language.9815 npmMIT