How to Use the PDF Munk MCP in OpenAI Agents SDK

Q: Can my agent use PDF Munk and OpenAI Agents SDK to process URLs directly?

Yes, the agent invokes generatepdffromurl to fetch any live web page and convert it into a PDF. This tool processes the page layout asynchronously and returns the generated document link.

Q: What is the best way to manage templates inside OpenAI Agents SDK with PDF Munk?

You should use listtemplates to let your agent inspect available layouts. Once it selects the right ID, it injects the payload variables using generatepdffromtemplate.

Q: Can I split large documents into individual pages?

The splitpdf tool allows your agent to break down multi-page files into separate documents. This is useful when your agent needs to analyze specific pages individually.

Generate, merge, and compress PDFs dynamically inside your OpenAI Agents SDK workflows with zero manual schema configuration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PDF Munk MCP to OpenAI Agents SDK

Create your Vinkius account to connect PDF Munk 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 Munk with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic HTML rendering via OpenAI Agents SDK

PDF Munk converts raw HTML strings directly into production-ready PDF documents inside your OpenAI Agents SDK runtime using the `generate_pdf_from_html` tool. Your agent reads database records, constructs the markup, and hands it off to this MCP Server to get a raw file back instantly. If you need to build from existing layouts, your OpenAI agent uses `generate_pdf_from_template` or fetches layout details via `get_template`. This prevents your agent from hallucinating layout structures and keeps design elements separated from execution logic.

Automated document assembly and compression

Merging multiple files into a single bundle is handled by the `merge_pdfs` tool without leaving your OpenAI Agents SDK Python execution context. The agent inspects your files, sequences them correctly, and calls this tool to combine them in one pass. To keep storage costs down, your OpenAI agent runs `compress_pdf` right after merging to minimize payload size. This reduces file sizes before transmitting them to users or uploading them to your cloud buckets.

Visual verification and watermarking tools

Applying visual security indicators to your documents is done via the `add_watermark` tool directly from your OpenAI Agents SDK workflow. You can programmatically stamp draft or confidential notices onto generated documents before they go out using this MCP Server. For visual debugging, your OpenAI agent calls `generate_screenshot` or `generate_image` to evaluate the layout quality. It then evaluates the layout quality directly within the run loop to check for rendering errors.

Setup guide

Set up PDF Munk 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 Munk tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives PDF Munk 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 Munk 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 Munk Agent",
            instructions="You have access to PDF Munk 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 Munk. 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 Munk 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 Munk MCP in OpenAI Agents SDK

The SDK auto-discover all twelve tools when you register the MCP Server endpoint. Setting the cache parameter to true prevents redundant network lookups during agent execution.

Yes, the agent invokes `generate_pdf_from_url` to fetch any live web page and convert it into a PDF. This tool processes the page layout asynchronously and returns the generated document link.

You should use `list_templates` to let your agent inspect available layouts. Once it selects the right ID, it injects the payload variables using `generate_pdf_from_template`.

The `split_pdf` tool allows your agent to break down multi-page files into separate documents. This is useful when your agent needs to analyze specific pages individually.

Your raw HTML payloads, template variables, and generated PDF files are processed in secure, ephemeral V8 isolates that wipe all data immediately after execution. No document content is ever cached or stored on persistent disks during the OpenAI Agents SDK run.

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