How to Use the PDF.co MCP in VS Code Copilot

Q: How do we share the PDF.co MCP Server configuration with our team in VS Code Copilot?

Create a .vscode/mcp.json file in your repository root and add the MCP Server definition. Once committed, any team member using VS Code Copilot with version 1.96 or higher can access the PDF.co tools automatically.

Q: How do we monitor long-running PDF.co jobs in VS Code Copilot?

When you execute a large conversion task, Copilot uses the checkjobstatus tool to poll the background process. It will update you on the progress directly in the chat window until the final file is ready.

Q: Can we inspect PDF metadata using PDF.co inside VS Code Copilot?

Yes, you can run the extractpdfmeta tool on any document in your workspace. Copilot will extract the metadata properties and display them as a clean JSON block in your editor context.

Share PDF.co tools with your entire team in VS Code Copilot to automate document parsing directly from your workspace.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PDF.co MCP to VS Code Copilot

Create your Vinkius account to connect PDF.co to VS Code Copilot — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PDF.co with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Share PDF.co tools across your team in VS Code Copilot

The `pdf_to_json`, `pdf_to_csv`, and `pdf_to_text` tools can be committed to your repository's `.vscode/mcp.json` file, giving your entire engineering team access to the same document processing tools. When a developer needs to inspect an invoice format, they ask Copilot to convert the file directly in their active workspace. This shared configuration ensures everyone uses the same API endpoints and parsing rules. Your developers don't need to set up individual API clients; they use the committed MCP Server configuration to run tests and verify document structures.

Secure and unprotect files within VS Code Copilot

The `protect_pdf` and `unprotect_pdf` tools let your team manage document security settings during development without using external desktop software. If you are testing a feature that requires encrypted inputs, you can ask Copilot to lock a test PDF with a password directly from the chat interface. This keeps your development environment self-contained. Copilot handles the encryption and decryption steps by calling the server, letting you focus on writing the code that handles these secure files.

Extract text from scans with VS Code Copilot

The `ocr_image` tool allows your team to extract text from scanned PDFs and images directly inside the editor. When you are writing code to parse incoming physical mail or scanned receipts, Copilot can run OCR on your sample assets to show you the expected text output. You don't need to write throwaway scripts to test OCR accuracy on new image files. This MCP Server lets Copilot run the OCR engine in real time, giving your team immediate feedback on text extraction quality before committing code.

Setup guide

Set up PDF.co MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the PDF.co MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the PDF.co tools listed. Try asking: "List my recent PDF.co transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "pdfco-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by PDF.co. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect PDF.co now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about PDF.co MCP in VS Code Copilot

Create a `.vscode/mcp.json` file in your repository root and add the MCP Server definition. Once committed, any team member using VS Code Copilot with version 1.96 or higher can access the PDF.co tools automatically.

Yes, you can select multiple PDF files in your workspace and ask Copilot to combine them. The agent will call the `merge_pdfs` tool and output the combined file path directly in your terminal or chat.

When you execute a large conversion task, Copilot uses the `check_job_status` tool to poll the background process. It will update you on the progress directly in the chat window until the final file is ready.

Yes, you can run the `extract_pdf_meta` tool on any document in your workspace. Copilot will extract the metadata properties and display them as a clean JSON block in your editor context.

All document payloads, JSON schemas, and text outputs are encrypted in transit using TLS 1.3. PDF.co processes the files in secure, ephemeral environments, ensuring that your company's proprietary document structures and text data are never stored or used to train models.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript