PDF.co Connector for AI agents.
12 live capabilities
Automate PDF conversion and high-fidelity OCR data extraction.
Waiting for input…
Why people use PDF.co
PDF.co OCR and Data Extraction for Accountants
This Connector lets your agent do that work for you. Just give your agent a link or a file, and it uses pdf_to_json or pdf_to_csv to pull out the exact data you need. You get a clean, structured list of information ready for your records without ever having to click a button.
What Vinkius changes
You stop manually processing documents and start letting your agent handle the file conversions and data extraction for you.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Automated Invoice Processing
An accountant has 50 scanned invoices to log.
- Real-world use case 02
Report Consolidation
A manager needs to combine 10 quarterly reports.
- Real-world use case 03
Data Scraping for Web Apps
A developer needs to pull text from a PDF for a web app.
Complete set · 12capabilities
The complete PDF.co capability set.
These are the exact actions your AI can choose when you ask it to work with PDF.co.
01—04
4 capabilities in this set.
Part of 12 available through PDF.co.
- 01 Capability
Check job status
See if your long-running document conversion is finished. It helps you stay on top of big batch jobs.
- 02 Capability
Pdf to csv
Turn PDF tables into CSV files. It's perfect for moving data into spreadsheets quickly.
- 03 Capability
Pdf to json
Convert PDF content into structured JSON. This makes it easy for your agent to read specific data points.
- 04 Capability
Pdf to text
Turn a PDF into plain text. Use this when you just need the raw words without any formatting.
05—08
4 capabilities in this set.
Part of 12 available through PDF.co.
- 05 Capability
Pdf to xml
Convert PDF files into XML format. This is great for legacy systems that require specific data structures.
- 06 Capability
Extract pdf meta
Pull metadata out of a PDF using AI. It helps you find hidden details in your files.
- 07 Capability
Get account info
Check your PDF.co account and credit balance. Use this to keep your production running smoothly.
- 08 Capability
Merge pdfs
Combine multiple PDF files into a single document. It saves you from manually stitching reports together.
09—12
4 capabilities in this set.
Part of 12 available through PDF.co.
- 09 Capability
Ocr image
Run OCR on an image file. This turns pictures of text into actual editable data.
- 10 Capability
Protect pdf
Add a password to a PDF. It keeps your sensitive documents secure with a simple command.
- 11 Capability
Split pdf
Split a large PDF into smaller files. This is useful for breaking down massive reports into manageable chunks.
- 12 Capability
Unprotect pdf
Remove a password from a PDF. Use this to make files accessible for your team.
Set up in minutes
One URL. Then ask PDF.co to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use PDF.co from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_uVxMMI3j4I5XvY70ujxxyTdKG0jtWoShDwpFOIBv/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it PDF.co, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable PDF.co for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_uVxMMI3j4I5XvY70ujxxyTdKG0jtWoShDwpFOIBv/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the PDF.co URL.
- Step 03
Save and start
Save the connection and enable PDF.co in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"pdfco": {
"url": "https://edge.vinkius.com/vk_preview_uVxMMI3j4I5XvY70ujxxyTdKG0jtWoShDwpFOIBv/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using PDF.co
Open Agent mode in chat and ask: "Using PDF.co, help me...". 12 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"pdfco": {
"url": "https://edge.vinkius.com/vk_preview_uVxMMI3j4I5XvY70ujxxyTdKG0jtWoShDwpFOIBv/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using PDF.co
Ask Copilot: "Using PDF.co, help me...". 12 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"pdfco": {
"url": "https://edge.vinkius.com/vk_preview_uVxMMI3j4I5XvY70ujxxyTdKG0jtWoShDwpFOIBv/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using PDF.co
Open Cascade and ask: "Using PDF.co, help me...". 12 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"pdfco": {
"url": "https://edge.vinkius.com/vk_preview_uVxMMI3j4I5XvY70ujxxyTdKG0jtWoShDwpFOIBv/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using PDF.co
Ask Cline: "Using PDF.co, help me...". 12 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add pdfco --transport http "https://edge.vinkius.com/vk_preview_uVxMMI3j4I5XvY70ujxxyTdKG0jtWoShDwpFOIBv/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using PDF.co
Ask Claude: "Using PDF.co, show me...". 12 tools are ready
Where the request belongs
Work PDF.co can move forward.
This is for the data person who spends half their day moving numbers from PDFs into spreadsheets or the ops lead stuck managing a mess of logistics documents.
Data Analyst
Extracts tabular data from monthly reports into CSVs without opening a single viewer.
Accountant
Automates invoice data extraction to keep the books updated in real-time.
Operations Manager
Merges and splits logistics files on the fly using natural language commands.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsPSPDFKit (Nutrient)
Professional PDF and document processing. generate, convert, OCR, and edit documents via the Nutrient API.
iLovePDF
Merge, split, compress, and convert PDF files with a complete toolkit that handles every document processing need online.
PDF Munk
Automate PDF and image generation via PDF Munk. convert HTML/URL to PDF, merge documents, and compress files directly from any AI agent.
Pdfcrowd
Convert HTML, web pages, and documents to PDF or images. Generate invoices and extract text from PDFs directly via AI.
Stirling PDF
Manage PDF documents via Stirling PDF. add watermarks, convert images to PDF, sign documents with certificates, and monitor server metrics directly.
AlgoDocs
AI document extraction orchestration. parse PDFs, images, and Word docs via AI.
Bring your own AI
Change the model, client or framework. Keep PDF.co connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about PDF.co.
The practical details behind the request, access and result.
How does PDF.co help with scanned documents?
It uses high-fidelity OCR to read text from images and scanned files, turning them into actual data your agent can understand.
Can I use PDF.co to turn my PDFs into spreadsheets?
Yes, you can use the pdf_to_csv capability to automatically convert tables in your documents into a format ready for Excel or Google Sheets.
Does PDF.co support extracting data from images?
It does. The ocr_image capability lets your agent read pictures of text and turn them into structured information.
How do I manage my PDF.co account using this Connector?
You can use the get_account_info capability to check your current balance and status directly within your chat interface.
Can I merge multiple files at once?
You can use the merge_pdfs capability to combine several documents into one master file using simple natural language commands.
Is there a way to see if my document conversion is done?
Yes, the check_job_status capability lets you see the progress of any long-running tasks while your agent works in the background.
Can I secure my documents with this Connector?
You can use protect_pdf to add passwords to your files, keeping your sensitive information private.
Can my AI automatically find and extract a specific table from a PDF?
Yes! Use the convert_to_csv or convert_to_json capabilities. Your agent will respond with the structured tabular data from the document in seconds, ready for analysis.
How do I find my PDF.co API Key?
Log in to your PDF.co account, navigate to the main dashboard, and you will find your unique secret API key (starting with your email reference or key string) there.
Does this support handwritten text recognition?
Absolutely. PDF.co's high-fidelity OCR engine is designed to handle both printed and handwritten text with high accuracy across multiple languages.
One connection away
Give your agent a direct line to PDF.co.
Connect PDF.co once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available