What can you do with this server?

PDF.co MCP Server lets you perform PDF/document conversion, editing, analysis, form handling, security, OCR/searchability, and file/job management through PDF.co API tools. * Convert PDFs to JSON, CSV, text, XLS/XLSX, XML, HTML, and images (JPG/PNG/WebP/TIFF). * Convert documents, spreadsheets, images, webpages, HTML, and emails (MSG/EML) to PDF; Excel tools include retiring CSV/JSON/HTML/TXT/XML converters and excel_to_pdf. * Edit PDFs: merge, split, add text/images/links/shapes/annotations, fill forms, and create fillable form fields. * Read PDF form field info, fill existing forms, and create new form elements. * Search PDFs for text (including regex) and find table coordinates. * Analyze PDFs: AI invoice parsing, attachment extraction, and PDF info such as pages, metadata, security, and form fields. * Add/remove password protection and configure encryption, permissions, and printing/copying restrictions. * Make scanned PDFs searchable via OCR or remove the text layer to make them non-searchable. * Upload local files to PDF.co and check or wait for asynchronous job completion.

Which integrations are available for this server?

Offers PDF conversion to XML format, allowing transformation of PDF content into structured XML data

How do I use PDF.co MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@PDF.co MCP Server convert this PDF to text so I can copy the content" 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.

PDF.co MCP Server

Official

by pdfdotco

Overview Schema Source Related Servers Discussions Admin

Python

Remote

PDF.co MCP

PDF.co MCP Server provides PDF.co API functionality through the Model Context Protocol (MCP), enabling AI assistants to easily perform various PDF processing tasks.

🚀 Key Features

📄 PDF Conversion Tools

PDF → Various Formats: Convert PDFs to JSON, CSV, Text, Excel (XLS/XLSX), XML, HTML, Images (JPG/PNG/WebP/TIFF)
Various Formats → PDF: Convert documents (DOC/DOCX/RTF/TXT), spreadsheets (CSV/XLS/XLSX), images, web pages, HTML, emails (MSG/EML) to PDF
Excel Conversions: Convert Excel files to PDF

🛠️ PDF Editing & Modification

PDF Merging: Combine multiple PDF files into one
PDF Splitting: Split PDFs by specific pages or page ranges
Add Annotations & Images: Add text, links, images, shapes to PDFs
Form Operations: Read PDF form field information, fill forms, create new form elements

🔍 PDF Search & Analysis

Text Search: Search text in PDFs (supports regular expressions)
Table Detection: Find table locations and coordinates in PDFs
AI Invoice Parser: Extract invoice data using AI
PDF Information: Get detailed information including metadata, page count, security info

🔒 Security & Accessibility

Password Protection: Add/remove password protection to PDFs
Searchability: Make PDFs searchable via OCR or remove text layers
Attachment Extraction: Extract attachments from PDFs

💼 File Management

File Upload: Upload local files to PDF.co servers
Job Status Tracking: Monitor progress and results of asynchronous operations

Related MCP server: Doc MCP Server

⚙️ Configuration

🔑 Get API Key

Sign up at PDF.co website
Get your API key from the dashboard

📦 Install UV

You need to install UV (a fast Python packaging tool) to use this MCP server:

macOS and Linux

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Alternative Installation Methods

Homebrew: brew install uv
PyPI with pipx: pipx install uv
PyPI with pip: pip install uv

For more installation options and details, see the UV installation guide.

Connect your client

Step-by-step guides with screenshots for each client are on developer.pdf.co:

Any other client that runs local MCP servers over STDIO uses the same three values: the command uvx, the argument pdfco-mcp, and the environment variable X_API_KEY. In JSON form:

{
  "mcpServers": {
    "pdfco": {
      "command": "uvx",
      "args": ["pdfco-mcp"],
      "env": {
        "X_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Desktop apps often do not see your terminal's PATH; if the server fails to start, use the full path to uvx as the command. uvx keeps the version it first resolved, so run uvx pdfco-mcp@latest once to pick up a new release.

🔧 Available Tools

PDF Conversion Tools

pdf_to_json: Convert PDF and scanned images into JSON representation with text, fonts, images, vectors, and formatting preserved
pdf_to_csv: Convert PDF and scanned images into CSV representation with layout, columns, rows, and tables
pdf_to_text: Convert PDF and scanned images to text with layout preserved
pdf_to_xls: Convert PDF and scanned images to XLS (Excel 97-2003) format
pdf_to_xlsx: Convert PDF and scanned images to XLSX (Excel 2007+) format
pdf_to_xml: Convert PDF and scanned images to XML format
pdf_to_html: Convert PDF and scanned images to HTML format
pdf_to_image: Convert PDF and scanned images to various image formats (JPG, PNG, WebP, TIFF)

Document to PDF Conversion Tools

document_to_pdf: Convert various document types (DOC, DOCX, RTF, TXT, XLS, XLSX, CSV, HTML, JPG, PNG, TIFF, WEBP) into PDF
csv_to_pdf: Convert CSV or spreadsheet files (XLS, XLSX) to PDF
image_to_pdf: Convert various image formats (JPG, PNG, TIFF) to PDF
webpage_to_pdf: Convert external webpage URL to PDF
html_to_pdf: Convert HTML to PDF
email_to_pdf: Convert email to PDF

Excel Conversion Tools

Retirement Notice — January 5, 2027
The following Excel conversion tools are scheduled for retirement on January 5, 2027, following the discontinuation of their underlying PDF.co API endpoints: excel_to_csv, excel_to_json, excel_to_html, excel_to_txt, excel_to_xml. These tools will remain available until the retirement date. After January 5, 2027, requests to their underlying API endpoints will no longer be supported. excel_to_pdf is not affected.

excel_to_csv: Convert Excel(XLS, XLSX) to CSV (retiring January 5, 2027)
excel_to_json: Convert Excel(XLS, XLSX) to JSON (retiring January 5, 2027)
excel_to_html: Convert Excel(XLS, XLSX) to HTML (retiring January 5, 2027)
excel_to_txt: Convert Excel(XLS, XLSX) to TXT (retiring January 5, 2027)
excel_to_xml: Convert Excel(XLS, XLSX) to XML (retiring January 5, 2027)
excel_to_pdf: Convert Excel(XLS, XLSX) to PDF

PDF Editing Tools

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
pdf_merge: Merge PDF from two or more PDF, DOC, XLS, images, even ZIP with documents and images into a new PDF
pdf_split: Split a PDF into multiple PDF files using page indexes or page ranges

PDF Form Tools

read_pdf_forms_info: Extracts information about fillable PDF fields from an input PDF file
fill_pdf_forms: Fill existing form fields in a PDF document
create_fillable_forms: Create new fillable form elements in a PDF document

PDF Search Tools

find_text: Find text in PDF and get coordinates. Supports regular expressions
find_table: Find tables in PDF and get their coordinates

PDF Analysis Tools

ai_invoice_parser: AI Invoice Parser: Extracts data from invoices using AI
extract_attachments: Extracts attachments from a source PDF file
pdf_info_reader: Get detailed information about a PDF document - number of pages, metadata, security, form fields, and more

PDF Security Tools

pdf_add_password: Add password protection to a PDF file
pdf_remove_password: Remove password protection from a PDF file

PDF Searchability Tools

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
pdf_make_unsearchable: Make existing PDF document non-searchable by removing the text layer from it

File Management Tools

upload_file: Upload a file to the PDF.co API
get_job_check: Check the status and results of a job. Status can be: working, success, failed, aborted, or unknown
wait_job_completion: Wait for a job to complete

📖 Usage Examples

Convert PDF to Text

Convert this PDF file to text: https://example.com/document.pdf

Merge Multiple Images into PDF

Create a PDF from these images: image1.jpg, image2.png, image3.jpg

Search for Specific Text in PDF

Find the word "contract" in this PDF document

Fill PDF Form Fields

Fill the name field in this PDF form with "John Doe"

Convert Web Page to PDF

Convert https://example.com webpage to PDF

Extract Invoice Data

Extract invoice information from this PDF using AI

Add Password Protection

Add password protection to this PDF file

📞 Support & Contact

PDF.co: https://pdf.co
PDF.co API Documentation: https://developer.pdf.co
Issue Reports: Please report issues through GitHub Issues

📄 License

This project is distributed under the MIT License.

Note: A valid PDF.co API key is required to use this tool. Create a free account at PDF.co to get your API key.

Available Tools

38 tools

ai_invoice_parserB

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

Inputs: url (required), api_key.

create_fillable_formsB

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

Inputs: url (required), annotations (required), name, api_key, +4 more.

csv_to_pdfC

Convert CSV or spreadsheet files (XLS, XLSX) to PDF.
Ref: https://developer.pdf.co/api/pdf-from-document/csv.md

Inputs: url (required), name, pages, api_key, +5 more.

document_to_pdfB

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

Inputs: url (required), name, pages, api_key, +5 more.

email_to_pdfC

Convert email to PDF.
Ref: https://developer.pdf.co/api/pdf-from-email.md

Inputs: url (required), api_key, margins, profiles, +5 more.

excel_to_csvB

Convert Excel(XLS, XLSX) to CSV.
Retiring on January 5, 2027: the underlying PDF.co API endpoint is being discontinued. The tool keeps working until that date and will be removed afterwards.
Ref: https://developer.pdf.co/api/convert-from-excel/csv.md

Inputs: url (required), name, api_key, profiles, +4 more.

excel_to_htmlB

Convert Excel(XLS, XLSX) to HTML.
Retiring on January 5, 2027: the underlying PDF.co API endpoint is being discontinued. The tool keeps working until that date and will be removed afterwards.
Ref: https://developer.pdf.co/api/convert-from-excel/html.md

Inputs: url (required), name, api_key, profiles, +4 more.

excel_to_jsonB

Convert Excel(XLS, XLSX) to JSON.
Retiring on January 5, 2027: the underlying PDF.co API endpoint is being discontinued. The tool keeps working until that date and will be removed afterwards.
Ref: https://developer.pdf.co/api/convert-from-excel/json.md

Inputs: url (required), name, api_key, profiles, +4 more.

excel_to_pdfC

Convert Excel(XLS, XLSX) to PDF.
Ref: https://developer.pdf.co/api/convert-from-excel/pdf.md

Inputs: url (required), name, api_key, profiles, +4 more.

excel_to_txtA

Convert Excel(XLS, XLSX) to TXT.
Retiring on January 5, 2027: the underlying PDF.co API endpoint is being discontinued. The tool keeps working until that date and will be removed afterwards.
Ref: https://developer.pdf.co/api/convert-from-excel/text.md

Inputs: url (required), name, api_key, profiles, +4 more.

excel_to_xmlA

Convert Excel(XLS, XLSX) to XML.
Retiring on January 5, 2027: the underlying PDF.co API endpoint is being discontinued. The tool keeps working until that date and will be removed afterwards.
Ref: https://developer.pdf.co/api/convert-from-excel/xml.md

Inputs: url (required), name, api_key, profiles, +4 more.

extract_attachmentsC

Extracts attachments from a source PDF file.
Ref: https://developer.pdf.co/api/pdf-extract-attachments.md

Inputs: url (required), api_key, password, profiles, +3 more.

fill_formsA

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

Inputs: url (required), fields (required), name, api_key, +4 more.

find_tableC

Find tables in PDF and get their coordinates.
Ref: https://developer.pdf.co/api/pdf-find/table.md

Inputs: url (required), pages, api_key, password, +4 more.

find_textC

Find text in PDF and get coordinates. Supports regular expressions.
Ref: https://developer.pdf.co/api/pdf-find/basic.md

Inputs: url (required), searchString (required), pages, api_key, +7 more.

get_job_checkA

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.

Inputs: job_id (required), api_key.

html_to_pdfB

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:
```html
<span style='font-size:10px'>Page <span class='pageNumber'></span> of <span class='totalPages'></span>.</span>

Inputs: html (required), name, footer, header, +11 more.

image_to_pdfC

Convert various image formats (JPG, PNG, TIFF) to PDF.
Ref: https://developer.pdf.co/api/pdf-from-image.md
```

Inputs: url (required), name, pages, api_key, +4 more.

pdf_add_annotations_images_fieldsB

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:

1. **annotations**: Add text, links, shapes, etc.
   Properties: text, x, y, size, pages, color, link, fontName, fontItalic, fontBold, fontStrikeout, fontUnderline

2. **images**: Add images or other PDF content
   Properties: url, x, y, width, height, pages

3. **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

Inputs: url (required), name, fields, images, +9 more.

pdf_add_passwordC

Add password protection to a PDF file.
Ref: https://developer.pdf.co/api/pdf-password/add.md

Inputs: url (required), owner_password (required), name, api_key, +15 more.

pdf_info_readerB

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

Inputs: url (required), api_key, password, profiles, +3 more.

pdf_make_searchableB

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

Inputs: url (required), lang, name, pages, +6 more.

pdf_make_unsearchableB

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

Inputs: url (required), name, pages, api_key, +5 more.

pdf_mergeB

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

Inputs: url (required), name, api_key, profiles, +3 more.

pdf_remove_passwordC

Remove password protection from a PDF file.
Ref: https://developer.pdf.co/api/pdf-password/remove.md

Inputs: url (required), name, api_key, password, +4 more.

pdf_splitC

Split a PDF into multiple PDF files using page indexes or page ranges.
Ref: https://developer.pdf.co/api/pdf-split/by-pages.md

Inputs: url (required), pages (required), name, api_key, +5 more.

pdf_to_csvC

Convert PDF and scanned images into CSV representation with layout, columns, rows, and tables.
Ref: https://developer.pdf.co/api/pdf-to-csv.md