How to Use the PDF.co MCP in OpenAI Agents SDK

Q: What is the best tool for extracting tables in this setup?

Use pdftocsv if your agent needs to feed data into a data analysis tool, or pdftojson if you want the agent to parse the layout structure directly.

Run secure, multi-agent document workflows using the PDF.co MCP Server with the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect PDF.co to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-agent document parsing with OpenAI Agents SDK

Stop letting one massive agent handle everything. Spin up a specialized parser agent that uses `pdf_to_json` to extract raw data, then hands off the clean output to your main reasoning agent. It keeps your token usage low and stops your system from wandering off track. Your agent discovers these tools dynamically over MCP. The SDK registers `pdf_to_text` and `pdf_to_csv` automatically, allowing your pipeline to switch tools based on the incoming file type without hardcoded routing.

Safe asynchronous execution with guardrails

Large documents take time to process. Instead of blocking your thread, have your agent trigger `pdf_to_xml` and hand off the tracking task to a monitor agent via MCP. The monitor uses `check_job_status` to poll the endpoint in the background. The SDK enforces strict validation before any tool runs. If an agent tries to pass a malformed URL to `ocr_image`, the built-in guardrails catch it before the API call even leaves your server, saving your credits.

Encrypted document delivery and compliance

Handling sensitive financial records requires strict control. Your agent can automatically run `protect_pdf` to lock down output files with passwords before saving them to your cloud storage. If you need to read incoming secure files, have your agent run `unprotect_pdf` first. This keeps your decryption keys isolated within the agent's execution context, so raw credentials never leak into your main logs.

Setup guide

Set up PDF.co MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all PDF.co tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives PDF.co tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate PDF.co tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="PDF.co Agent",
            instructions="You have access to PDF.co tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You don't need to pass keys directly to your agents. Vinkius handles the API credentials securely at the proxy level, so your Python code only needs the single endpoint token during SDK initialization.

Yes. While the SDK auto-discovers all 12 tools, you can filter the tool list when initializing your agent instance to prevent it from calling tools like `unprotect_pdf` or `split_pdf`.

For heavy files, don't run synchronous calls. Have your agent initiate the process, grab the job ID, and use `check_job_status` to poll for completion while the main agent handles other tasks.

Use `pdf_to_csv` if your agent needs to feed data into a data analysis tool, or `pdf_to_json` if you want the agent to parse the layout structure directly.

All PDF documents processed through this MCP server are handled in ephemeral V8 Isolate sandboxes on Vinkius. Files are fetched via secure URLs, processed, and immediately discarded, leaving no persistent footprint on the server.

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