PDF.co

PDF.co MCP Server exposes PDF.co’s PDF processing capabilities through the Model Context Protocol (MCP), letting your AI assistants perform PDF conversions, edits, searches, security tasks, and more via a lightweight, scalable server setup.

How to use

You interact with the PDF.co MCP server through an MCP client by starting the local MCP server and directing your client to connect to it. The server provides a rich set of tools for PDF conversion, editing, search, analysis, security, and file management. When you start the server, you’ll supply your API key so the MCP client can authenticate requests to PDF.co. Use the client to invoke specific tools by name (for example, convert a PDF to text, extract data from a PDF, or merge multiple PDFs) and receive structured results.

How to install

Prerequisites: a system with curl and a compatible shell, plus Python tooling for the MCP runtime. You will also need a PDF.co API key to authorize requests.

Install the MCP runtime tool UV, which is used to run MCP servers. Choose the method that matches your operating system.

macOS and Linux Install UV via a script:

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

Windows Install UV via PowerShell:

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

Alternative installation methods if you prefer package managers:

# Homebrew
brew install uv

# PyPI with pipx
pipx install uv

# PyPI with pip
pip install uv

Once UV is installed, you are ready to configure and run the PDF.co MCP server.

Configuration and running the server

Create or update your MCP client configuration to point to the PDF.co MCP server. The following setup demonstrates how to register the server in a local MCP client, using the UV-based runtime.

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

Start and test the server

With the configuration in place, start the MCP server using the runtime shown in your client configuration. The server will authenticate using your API key and expose the PDF.co MCP tools to your client for use in your workflows.

Notes on usage and capabilities

The PDF.co MCP server exposes a wide range of tools for PDF handling, including conversion to and from PDF, editing (merging, splitting, annotations, and form operations), search and analysis (text search, table detection, AI invoice parsing), security features (password protection, OCR-based searchability), and file management (uploading files and tracking job status). Each tool is invoked by name from your MCP client, and results are returned in structured formats suitable for downstream processing.

Security and environment

Protect your API key and restrict access to the MCP server in your environment. The API key is required to authorize requests to PDF.co. Use the provided environment variable X_API_KEY to pass your key to the MCP server.

Troubleshooting and tips

If you encounter connection issues, verify that the MCP runtime (uvx) is running and that the API key is correctly set in your environment. Check that your MCP client configuration references the same server name and that any firewall rules allow local communication between the client and the MCP runtime.

Configuration reference

Use the following configuration snippet to register the PDF.co MCP server in your MCP client. Ensure you replace YOUR_API_KEY_HERE with your actual API key.

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

Available tools

pdf_to_json

Convert PDF and scanned images into a JSON representation preserving text, fonts, images, vectors, and formatting.

pdf_to_csv

Convert PDF and scanned images into a CSV representation with layout, columns, rows, and tables.

pdf_to_text

Convert PDF and scanned images to text with layout preservation.

pdf_to_xls

Convert PDF and scanned images to XLS (Excel 97-2003).

pdf_to_xlsx

Convert PDF and scanned images to XLSX (Excel 2007+).

pdf_to_xml

Convert PDF and scanned images to XML.

pdf_to_html

Convert PDF and scanned images to HTML.

pdf_to_image

Convert PDF and scanned images to image formats like JPG, PNG, WebP, TIFF.

document_to_pdf

Convert various documents to PDF.

csv_to_pdf

Convert CSV or spreadsheet files to PDF.

image_to_pdf

Convert image formats to PDF.

webpage_to_pdf

Convert an external webpage URL to PDF.

html_to_pdf

Convert HTML to PDF.

email_to_pdf

Convert email to PDF.

excel_to_csv

Convert Excel files to CSV.

excel_to_json

Convert Excel files to JSON.

excel_to_html

Convert Excel files to HTML.

excel_to_txt

Convert Excel files to TXT.

excel_to_xml

Convert Excel files to XML.

excel_to_pdf

Convert Excel files to PDF.

pdf_add_annotations_images_fields

Add text, images, forms, links, and other elements; modify PDFs and fill forms.

pdf_merge

Merge multiple PDFs or other supported inputs into a single PDF.

pdf_split

Split a PDF into separate files by pages or ranges.

read_pdf_forms_info

Extract form field information from a PDF.

fill_pdf_forms

Fill existing form fields in a PDF.

create_fillable_forms

Create new fillable form elements in a PDF.

find_text

Find text in PDFs with optional regular expressions and return coordinates.

find_table

Find tables in PDFs and get their coordinates.

ai_invoice_parser

AI-based extraction of invoice data from PDFs.

extract_attachments

Extract attachments from PDFs.

pdf_info_reader

Get detailed information about a PDF (pages, metadata, security, forms, etc.).

pdf_add_password

Add password protection to a PDF.

pdf_remove_password

Remove password protection from a PDF.

pdf_make_searchable

Run OCR to make a PDF searchable and add an invisible text layer.

pdf_make_unsearchable

Remove the text layer to make a PDF non-searchable.

upload_file

Upload a file to the PDF.co API.

get_job_check

Check the status and results of an asynchronous job.

wait_job_completion

Wait for a job to complete.