How to Use the PDF.co MCP in Cursor

Q: How do I configure the PDF.co MCP Server in Cursor?

Create a .cursor/mcp.json file in your project root or update your global settings to include the MCP Server configuration. Once added, enable Agent mode in the chat panel to let Cursor call the PDF.co tools.

Q: Can Cursor use PDF.co to convert a PDF to CSV during a coding session?

Yes, you can ask Cursor to run the pdftocsv tool on a test document. The editor will execute the tool, display the CSV output in your chat, and help you write the code to parse that specific CSV structure.

Q: Can I check my PDF.co credit balance inside Cursor?

Yes, you can run the getaccountinfo tool through the Cursor terminal or chat interface. This tells you exactly how many credits you have left before executing expensive processing tasks.

Generate code that processes PDFs by letting Cursor call PDF.co tools to inspect schemas and run live tests.

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 Cursor

Create your Vinkius account to connect PDF.co to Cursor — 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Generate code with live PDF.co schemas in Cursor

The `pdf_to_json` and `pdf_to_xml` tools let Cursor inspect the exact structure of your target files while you write code. Instead of guessing the JSON keys or writing mock objects, your agent calls the tool on a sample document and uses the actual API response to write your parsing scripts. This changes how you build integrations. Cursor writes the TypeScript or Python code using the real keys returned by the API, which means your code runs correctly on the first try without debugging schema mismatches.

Extract PDF metadata directly inside your editor

The `extract_pdf_meta` tool retrieves document metadata, layout details, and structural properties to feed directly into your editor's context. When you are writing a document pipeline, Cursor uses this tool to check the page count, encryption status, or author of test files without forcing you to open an external viewer. Having this metadata inside your workspace keeps you focused. You can quickly verify if a test file is password-protected or check if it needs to go through `unprotect_pdf` before running your main parsing loop.

Test document pipelines using this Cursor MCP Server

The `merge_pdfs` and `split_pdf` tools let you prepare test fixtures and mock datasets directly within Cursor's agent mode. If you need to test how your application handles a 100-page document versus a 2-page document, you can ask the editor to split your source files on the fly. You don't have to leave the editor to run command-line utilities or Python scripts to prep your files. This MCP Server gives your editor direct access to the cloud processing engine, making test data preparation a natural part of your coding flow.

Setup guide

Set up PDF.co MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the PDF.co MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent PDF.co transactions." If the MCP tools are loaded correctly, Cursor will call the PDF.co tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Create a `.cursor/mcp.json` file in your project root or update your global settings to include the MCP Server configuration. Once added, enable Agent mode in the chat panel to let Cursor call the PDF.co tools.

Yes, you can ask Cursor to run the `pdf_to_csv` tool on a test document. The editor will execute the tool, display the CSV output in your chat, and help you write the code to parse that specific CSV structure.

When processing large files, Cursor calls the conversion tool and uses `check_job_status` to track the background job. The editor waits for the job to finish before writing code based on the output.

Yes, you can run the `get_account_info` tool through the Cursor terminal or chat interface. This tells you exactly how many credits you have left before executing expensive processing tasks.

Your documents, PDFs, and images are transmitted over secure HTTPS connections to the PDF.co cloud API. The data is processed in volatile memory, and temporary files are automatically purged, keeping your proprietary code fixtures and document data secure.

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