PDF.co is a REST API platform for PDF automation including PDF extraction, generation, editing, splitting, merging, form filling, barcode processing, OCR, document parsing, file conversion (PDF to Excel/CSV/JSON/XML/HTML/Image and vice versa), and AI-powered invoice parsing.
PDF.co is a REST API platform for PDF automation including PDF extraction, generation, editing, splitting, merging, form filling, barcode processing, OCR, document parsing, file conversion (PDF to Excel/CSV/JSON/XML/HTML/Image and vice versa), and AI-powered invoice parsing. On Nagent, PDF.co is exposed as a fully-configurable documents integration that any agent can call — 35 actions, and API key authentication. No code is required to wire PDF.co into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use PDF.co to automate the kinds of tasks documents teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire PDF.co into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against PDF.co, with input parameters and output schema. Drop these into any step of an agent built in Helix.
PDF_CO_ACCOUNT_BALANCE_INFOTool to get account balance info. Use after authenticating to check remaining credits.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_BARCODE_GENERATEDEPRECATED: Use PDFCOPostBarcodeGenerate instead. Tool to generate barcode images (QR, Code128, Code39, PDF417, etc.). Use when you need to encode data into barcodes on the fly.
Input parameters
Filename for the generated barcode (extension added automatically).
Barcode type (e.g., Code128, QRCode, Code39, PDF417).
Data/content to encode in the barcode.
Process request asynchronously.
Margin (white border) size around barcode in pixels.
Display human-readable text below the barcode.
Font name for human-readable text (e.g., 'Arial').
Font size (points) for human-readable text.
Barcode background color (hex or rgba).
Barcode foreground color (hex e.g., '#000000' or rgba string).
Image resolution in DPI.
Aspect ratio (width/height) for 2D barcodes.
Password to protect PDF if output format is 'pdf'.
Width of the barcode image in pixels.
Output image format ('png', 'jpg', 'pdf').
Height of the barcode image in pixels.
Treat barcode value as case-sensitive.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_CONVERT_EXCEL_TO_CSVTool to convert an Excel file (XLS/XLSX) to CSV. Use when you have a public Excel file URL and need CSV output. Inline option returns data inline; otherwise provides download URL.
Input parameters
Link to source XLS or XLSX file to be converted to CSV
Desired name for the output CSV file
Pages to convert (e.g., '0-2,4'), default is all pages
If true, returns CSV data inline; otherwise returns URL to CSV
Password for a protected Excel file, if applicable
Conversion profiles in JSON format, see PDF.co docs for structure
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_CONVERT_EXCEL_TO_HTMLTool to convert an Excel file to HTML. Use when you have an Excel URL and need HTML output.
Input parameters
URL to the source Excel file (xls, xlsx, or csv).
Name for the resulting HTML file (e.g., 'report.html').
Set to true to run the conversion asynchronously.
Conversion profiles as a JSON string.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_CONVERT_EXCEL_TO_JSONTool to convert an online Excel or CSV file to JSON format. Use when you have a public file URL and need structured data extraction.
Input parameters
Public URL of the source Excel/CSV file.
Desired name for the generated JSON file.
Comma-separated page indices or ranges to process, e.g., '1,3-5'.
Password for password-protected files.
Custom processing profiles in JSON format.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_CONVERT_EXCEL_TO_TEXTTool to convert Excel files to plain text. Use after providing an Excel file URL to extract spreadsheet content.
Input parameters
Link to the source Excel file (xls, xlsx, or csv).
Optional name for the output file.
Comma-separated list of sheet indices to convert, e.g., '0,2'.
Set to true to return data inline in response instead of URL.
Set to true to encrypt the resulting file.
Password for password-protected Excel files.
Conversion profiles in JSON format.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_CONVERT_EXCEL_TO_XMLTool to convert an Excel file to XML. Use when needing XML output from xls/xlsx/csv synchronously or asynchronously.
Input parameters
URL to the source file (xls, xlsx or csv).
Output file name.
Set true to run asynchronously, returning a jobId.
Set true to return XML inline, otherwise returns file URL.
Callback URL for async mode, used when async is true.
Profiles settings.
Link expiration time in minutes.
HTTP auth password for source URL.
HTTP auth user name for source URL.
Worksheet index as a string (0-based, e.g. '0' for the first worksheet).
Initialization vector for decryption.
Initialization vector for encryption.
Decryption key.
Encryption key.
Decryption algorithm (AES128, AES192, AES256).
Encryption algorithm (AES128, AES192, AES256).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_DOCUMENT_PARSERTool to parse documents based on predefined templates to extract structured data. Use when you need to extract structured fields from a PDF by supplying a custom template.
Input parameters
Public URL of the PDF to parse. Required if not uploading a file. Must be a publicly accessible HTTP/HTTPS URL or a file previously uploaded to PDF.co storage.
Raw PDF file bytes to upload directly. Required if not providing a URL.
Custom name for the output/result file.
Comma-separated page indices or ranges to process (e.g., '0,2-4'). If not specified, all pages are processed.
Return parsed results inline in the response body instead of generating a file URL.
Password for protected PDF files.
Inline YAML/JSON parsing template to extract structured data. The template defines fields to extract using regex patterns, rectangles, or static values. Example format: {"templateVersion": 3, "templatePriority": 1, "sourceId": "invoice", "fields": {"total": {"type": "regex", "expression": "TOTAL{{Spaces}}({{Number}})"}}}
Run parsing asynchronously and return a result URL instead of inline data.
Output format for parsed data: JSON, CSV, or XML. Default is JSON.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_FILE_UPLOADTool to upload a local file or remote URL to PDF.co, returning a hosted URL for downstream processing. Use when a PDF.co tool (e.g., PDF_CO_PDF_FROM_HTML) requires a remote URL but you have a local file.
Input parameters
URL of the file to upload to PDF.co. The file will be downloaded from this URL and uploaded. Either 'url' or 'file' must be provided, but not both.
File to upload to PDF.co. Either 'file' or 'url' must be provided, but not both.
Optional custom filename to assign on PDF.co (defaults to the file's original name).
Whether to execute the upload asynchronously (defaults to false).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_JOB_CHECKTool to check status and result of an asynchronous job. Use after submitting a job to poll for completion.
Input parameters
Set true to forcibly check long-running jobs. When true, returns 'unknown' for invalid job IDs instead of 'working'.
The unique identifier of the asynchronous job to check status for
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_ADDTool to add content to an existing PDF. Use when you need to overlay text, images, barcodes, or links before distributing the file.
Input parameters
Link to the source PDF file
Desired name for the result PDF file
Comma-separated page indices (e.g., '0,2-4') to process; defaults to all pages
List of objects to add (text, image, barcode, link, document, etc.). See API docs for structure.
Password for protected PDF, if needed
Run the process asynchronously; if true, returns a jobId for status checking
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_CHANGE_TEXT_SEARCHABLETool to make PDF text searchable using OCR. Use when you need to add a searchable text layer to scanned or image-only PDF documents.
Input parameters
Public URL of the source PDF file.
Comma-separated rectangle coordinates 'left,top,width,height' to limit OCR.
Single 0-indexed page number to process (e.g., '0' for the first page). The /pdf/makesearchable endpoint does not accept page ranges or comma-separated lists and will return HTTP 450 'Invalid page range specified' for values like '0-2' or '0,1'. Omit this field to OCR every page.
Whether to return the processed PDF data inline (base64) or as a URL. Set to true for inline response, false for URL.
Language code for OCR (default: eng).
Password for encrypted PDF, if applicable.
JSON string with advanced OCR profiles and configurations.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDFCO_POST_BARCODE_GENERATETool to generate high quality barcode images in 45+ formats including QR Code, Code 128, Code 39, and more. Use when you need to create barcodes with customization options like rotation, decoration images for QR codes, or async processing.
Input parameters
Output filename for the generated barcode image.
Barcode format to generate. Defaults to QRCode.
Enable background processing; returns jobId for status checks. Defaults to false.
The string value to be encoded into the barcode.
Return results within response (true) or return URL (false). Defaults to false.
Enable encryption for the output file.
Webhook URL to receive results when async operation completes.
Output link expiration time in minutes. Defaults to 60.
Rotation angle in degrees. Defaults to 0.
Image URL for logo insertion within QR codes.
Set to 'base64' for base64-encoded output.
Caption text font and size. Defaults to 'Arial, 12'.
Narrow bar width in pixels. Defaults to 3.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDFCO_POST_FILE_UPLOAD_BASE64Tool to create a temporary file using base64-encoded source data. Use when you need to upload file content as base64 to PDF.co for downstream processing. Temporary files are automatically deleted after 1 hour (or custom expiration time).
Input parameters
Base64-encoded file bytes with data URI prefix. Must include format like 'data:image/gif;base64,R0lGODlh...' or 'data:text/plain;base64,SGVsbG8gV29ybGQh...'
Custom file name for the output. If not provided, a default name will be used.
Link expiration time in minutes. Default is 60 minutes. Maximum varies by subscription plan. The temporary file is automatically deleted after expiration.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_DELETE_PAGESTool to delete specific pages from a PDF file. Use when you need to remove unwanted pages before further processing.
Input parameters
URL or base64-encoded content of the source PDF.
Optional name for the resulting PDF file.
Comma-separated list of page indices or ranges to delete (1-based). E.g., '1,3-5' to delete pages 1, 3, 4, and 5.
Password for protected PDF file.
Optional JSON string for advanced configuration.
Process request asynchronously. If true, returns a job ID instead of immediate URL.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_EXTRACT_ATTACHMENTSTool to extract embedded attachments from a PDF. Use when you need to retrieve embedded files from a PDF after uploading.
Input parameters
URL of the input PDF file to process.
If true, returns attachment data inline; otherwise returns URLs.
Webhook URL for receiving async results.
Password for protected PDF file (if applicable).
Run processing asynchronously. If true, returns a jobId for async processing.
Set the expiration time for the output link in minutes. Default is 60.
HTTP authentication password for accessing the source URL.
HTTP authentication username for accessing the source URL.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_FINDTool to find text in a PDF document. Use when you need to locate keywords or regex patterns and get their page positions.
Input parameters
Publicly accessible URL of the PDF file to search.
Comma-separated page ranges to search, e.g., '1-3,5'.
Password for protected PDF, if applicable.
Advanced JSON configuration for PDF processing.
Whether to treat searchString as a regular expression (default: false).
Keyword or regex pattern to find in the document.
Whether the search is case-sensitive (default: false).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_FORMS_INFO_READERTool to extract form field information from a PDF. Use when you need to retrieve names, types, and values of form fields. Returns field names, types (CheckBox, EditBox, RadioButton, ComboBox), values, and position coordinates.
Input parameters
Publicly accessible URL of the PDF file containing form fields.
If true, runs the job asynchronously and returns a jobId for status checking.
Password for encrypted PDF, if applicable.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_FROM_DOCUMENT_TXTTool to convert a plain text (.txt) file to PDF. Use when you have a public URL to a text file; raw inline text is not accepted by the endpoint.
Input parameters
Direct public URL to the source text (.txt) file. The endpoint only accepts a downloadable URL; raw/inline text is not supported and will return HTTP 400 'Invalid input parameters'. Upload the text first (e.g. via PDF.co file upload) and pass the resulting URL here.
Name of the resulting PDF file (e.g., 'result.pdf').
Optional JSON-formatted string with advanced API options.
Run processing asynchronously; if true, returns a jobId for status checking.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_FROM_EMAILTool to convert email files (.eml/.msg) to PDF. Use when you need to transform standalone email messages into PDF documents.
Input parameters
Direct URL to the input EML or MSG file. Must be a publicly reachable URL; local file paths and raw content strings are not accepted.
Optional name for the resulting PDF file.
Advanced configuration as a JSON-formatted string (must be a string, not an object). Only profile keys documented by PDF.co for the email-to-PDF endpoint are accepted; unsupported keys return a 444 'Profiles parsing error'. See samples at https://docs.pdf.co/api-reference/profiles. Leave unset unless you have a valid profile.
Run processing asynchronously; if true, returns a jobId for status checking.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_FROM_HTMLTool to convert HTML code or webpage URL into a PDF document. Use when you need to capture a webpage or HTML snippet as a PDF file.
Input parameters
The HTML page or resource URL to convert into PDF. Must be a reachable HTTP(S) URL; raw HTML strings and local file paths are not accepted. Upload local HTML files first to obtain a URL.
Desired output filename for the PDF result.
Run conversion as background job; returns jobId when true.
HTML snippet for page footers applied to each page.
HTML snippet for page headers applied to each page.
Custom page margins in '{top} {right} {bottom} {left}' format (units: px, mm, cm, in).
Webhook URL to receive asynchronous results when async=true.
Advanced conversion profiles/settings as JSON string.
CSS media type: 'print', 'screen', or 'none'.
Paper size: standard like 'Letter', 'Legal', 'A4'–'A6', or custom '200px 300px', '8in 10in'.
Expiration time in minutes for the output file link.
Document orientation: 'Portrait' or 'Landscape'.
Include background graphics (colors/images) if true.
If true, speeds up conversion by not waiting for full page load.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_INFO_READERTool to retrieve detailed information and metadata of a PDF. Use when you need page count, author, encryption details, and other document properties.
Input parameters
URL to the source PDF file
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_MERGETool to merge multiple PDF files into one document. Use when you need to combine several PDF URLs into a single PDF file.
Input parameters
Optional name for the resulting PDF file (must end with .pdf)
Comma-separated string of PDF URLs or a list of PDF URLs to merge. Each URL must point to a publicly accessible or presigned PDF file.
(Advanced) Custom JSON profiles for processing.
Run the merge asynchronously; if true returns a jobId for status checking.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_ROTATETool to rotate selected pages in a PDF. Use when you need to adjust the orientation of specific pages in an online PDF file before further processing.
Input parameters
URL of the source PDF file to rotate
Optional filename for the resulting PDF (should end with .pdf)
Rotation angle in degrees; must be one of 90, 180, or 270
Comma-separated list of page indices or ranges to rotate (e.g., '0,2-5')
Password for encrypted PDFs, if required
Run the operation asynchronously; if true, returns a jobId for status checking
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_SEARCH_AND_DELETE_TEXTTool to search for and delete text in a PDF by keyword or regex. Use when you need to remove sensitive or unwanted text from a PDF document.
Input parameters
URL or base64 content of the source PDF file.
Desired output filename for the PDF result.
Run operation asynchronously. Returns jobId if true.
Comma-separated list of page indices or ranges to process (0-based), e.g., '0,2-5'.
Treat searchString as regular expression.
Password for protected PDF if required.
Text string or regex pattern to search and delete.
Enable case-sensitive matching. Default is true.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_SEARCH_AND_REPLACE_TEXTTool to search for and replace text in a PDF document. Use when you need to update specific text instances within an existing PDF file (e.g., changing invoice numbers).
Input parameters
Publicly accessible URL of the source PDF file.
Optional name for the resulting PDF file.
Set to true to run process asynchronously (returns jobId).
Password for protected PDF, if required.
Enable regular expression search if true.
Text to search for in the document.
Text to replace each found occurrence with.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_SPLITTool to split a PDF into multiple files by page ranges. Use when you need to extract specific pages or page ranges from a PDF.
Input parameters
Public URL of the PDF file to split.
PDF file to upload for splitting instead of using a URL.
Base name for output files; each part receives a suffix.
Comma-separated or dash page ranges to split, e.g. '1-2,4'. 1-based indexing; omit to split all pages.
Return split documents inline (base64) instead of URLs.
Webhook URL for async notifications; only used when run_async is True.
Owner password for encrypted PDF files, if any.
Advanced processing profiles as JSON-formatted dict.
Run processing asynchronously; returns jobId instead of immediate results.
Minutes before temporary output links expire; default is service default.
HTTP basic auth password if the source URL is protected.
HTTP basic auth username if the source URL is protected.
Base64-encoded IV for output data encryption.
Set to 'base64' to return split PDFs as base64 strings.
Base64-encoded key for output data encryption.
Algorithm for user-controlled output encryption (AES128, AES192, AES256).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_TO_CSVTool to convert PDF or scanned images to CSV format. Use when you need to extract tabular data from a PDF into CSV format.
Input parameters
Link to the PDF file to be converted.
Language for OCR text recognition (e.g., 'eng', 'deu').
Optional name for the output CSV file (must end with .csv).
Comma-separated page indices or ranges to convert (e.g., '1,3-5').
If true, returns CSV data inline; otherwise returns a URL to the CSV.
If true, encrypts the output CSV file.
Password for protected PDF files, if required.
Advanced conversion settings in JSON format.
Run job asynchronously; returns jobId for status checking.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_TO_HTMLTool to convert PDF documents to HTML. Use when you need an HTML rendition of a PDF or scanned image.
Input parameters
URL to the source PDF file. Must be a publicly accessible HTTP/HTTPS URL (without authentication) or a file previously uploaded to PDF.co storage. Local file paths (file:// URLs) are not supported - use the PDF_CO_FILE_UPLOAD action first to upload local files to PDF.co, then use the returned URL here.
Binary content of the PDF file to upload as an alternative to 'url'.
Desired name for the resulting HTML file (e.g., 'result.html').
Comma-separated page indices or ranges to convert (e.g., '0,2-4').
If true, returns raw HTML in the 'body' field instead of a URL link.
Whether to encrypt the output HTML file.
Password for protected PDF files, if required.
Additional conversion profiles as a JSON string.
Set to true to run the conversion asynchronously.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_TO_IMAGETool to convert PDF pages to images (PNG, JPG, TIFF). Use when you need image previews of PDF content.
Input parameters
Resolution in DPI for the output images (1-300).
Link to the source PDF file.
Run processing asynchronously. Returns jobId when true.
Comma-separated list of page indices or ranges to convert. For example: '1,3-5' to convert pages 1, 3, 4, and 5.
Password for protected PDF files, if required.
Custom JSON profiles for advanced conversion options.
Output image format: PNG (default), JPG, or TIFF.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_TO_JSONTool to convert PDF or scanned images to JSON format. Use when you need a structured JSON representation of PDF content.
Input parameters
Link to the PDF file to be converted.
Binary content of the PDF file to convert.
Optional name for the output JSON file (should end with .json).
If true, runs the job asynchronously; returns jobId for status checking.
Comma-separated page indices or ranges to convert (e.g., '1,3-5').
If true, returns JSON data inline; otherwise returns a URL.
Password for protected PDF files, if required.
Advanced conversion configuration in JSON format.
Optional text to search for in the PDF before conversion.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_TO_TEXTTool to convert PDF or scanned images to plain text. Use when you need raw text output preserving layout.
Input parameters
URL to the source PDF or image file. Must be a publicly accessible HTTP/HTTPS URL (without authentication) or a file previously uploaded to PDF.co storage. Local file paths (file:// URLs) are not supported - use the PDF_CO_FILE_UPLOAD action first to upload local files to PDF.co, then use the returned URL here.
OCR language(s) code, e.g. 'eng', or 'eng+deu'.
Desired name for the output file (e.g. 'result.txt').
Extraction rectangle in format '{x} {y} {width} {height}'.
Comma-separated page indices or ranges to process (e.g. '0,2-4').
Return text inline in response instead of URL.
Unwrap lines into a single line within table cells (only when lineGrouping='1').
Webhook URL to receive callback when async=true.
Password for protected PDF files.
Run process asynchronously; returns jobId if true.
Expiration time in minutes for the output file link.
HTTP auth password for source URL.
HTTP auth username for source URL.
Line grouping mode: '1', '2', or '3'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_TO_XLSTool to convert PDF or scanned images to XLS format. Use when you need to extract tabular data into an Excel spreadsheet.
Input parameters
Link to the PDF file to be converted.
Optional name for the output XLS file (must end with .xls).
Comma-separated page indices or ranges to convert (e.g., '1,3-5').
Password for protected PDF files, if required.
Advanced conversion settings in JSON format.
Run job asynchronously; returns jobId for status checking.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_TO_XLSXTool to convert PDF or scanned images to XLSX (Excel) format. Use when you need structured spreadsheet output from a PDF.
Input parameters
Link to the PDF file to be converted.
Optional name for the output XLSX file (must end with .xlsx).
Run job asynchronously; returns processId for status checking.
Comma-separated page indices or ranges to convert (e.g., '1,3-5').
If true, returns XLSX data inline; otherwise returns a URL to the XLSX.
If true, encrypts the output XLSX file.
Password for protected PDF files, if required.
Advanced conversion settings in JSON format.
Expiration time for the output link in minutes (default is 60).
Optimization mode, e.g., 'ocr'.
Set to true if column indices in profiles are zero-based.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PDF_CO_PDF_TO_XMLTool to convert PDF or scanned images to XML format. Use when you need to extract structured data from PDF into XML.
Input parameters
Link to the PDF file to be converted.
Comma-separated page indices or ranges to convert (e.g., '1,3-5').
Password for protected PDF files, if required.
Advanced conversion settings in JSON format.
Run job asynchronously; returns jobId for status checking.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 57 agents privately built on Nagent that already use PDF.co.
Build on Nagent
Connect PDF.co to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find PDF.co, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, PDF.co is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once PDF.co is connected, you configure its 35 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop PDF.co steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a PDF.co event fires, the agent kicks off automatically.
Every PDF.co action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While PDF.co ships with 35 pre-built documents actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching PDF.co together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build PDF.co-based workflows tailored to your business.