How to Use the Docamatic MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK system handle document templates dynamically via Docamatic?

Yes. Your agent can call listavailablebuiltintemplates to discover what layouts are active, and then use generatepdffromtemplate to inject your application's raw JSON payload into the chosen template.

Q: Can I merge documents generated from raw HTML?

Yes. Your agent can use generatepdffromhtml to render your custom HTML layouts, and then pass those output paths to mergemultiplepdfs to combine them into a single file.

Build OpenAI Agents SDK workflows that generate, modify, and merge PDFs directly through our managed MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Docamatic MCP to OpenAI Agents SDK

Create your Vinkius account to connect Docamatic to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Docamatic with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate PDF generation in OpenAI Agents SDK

`generate_pdf_from_template` is the core tool that lets your OpenAI Agents SDK system build invoices and packing slips by injecting JSON data into pre-designed layouts. Your agents can call this tool to turn raw transaction data into polished, client-ready documents instantly. By using this MCP server, your system skips the overhead of managing Chrome headless instances or complex HTML rendering libraries. The agent simply passes the raw data, and Docamatic handles the heavy lifting, returning a clean PDF URL that your agent can immediately pass to the next step in your workflow.

Combine and modify documents on the fly

`merge_multiple_pdfs` and `add_elements_to_pdf` give your agents the power to stitch separate documents together and stamp extra text or images onto existing files. This means an agent can generate a cover page, append a multi-page report, and stamp a watermark on the final file in one continuous sequence. You get complete control over the final output without writing brittle file-manipulation script blocks. Because the OpenAI Agents SDK manages the tool execution state, your agents can inspect the generated history using `list_generation_history` to verify that everything was assembled correctly before finalizing the run.

Render web pages and HTML to high-res images

`generate_image_from_html` and `take_web_screenshot` allow your agents to capture visual snapshots of live websites or raw HTML blocks. This is particularly useful when your agent needs to archive a dashboard state or generate a visual preview of an invoice before sending it to a customer. The agent handles the tool call, and our sandbox renders the target page, capturing every pixel exactly as a real browser would. Your agent gets a clean image file back, ready to be analyzed or stored, bypassing all the typical headaches of running headless browsers in production.

Setup guide

Set up Docamatic 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 Docamatic tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Docamatic 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="Docamatic Agent",
            instructions="You have access to Docamatic 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 Docamatic. 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 Docamatic 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 Docamatic MCP in OpenAI Agents SDK

Install the SDK using pip install openai-agents. Then, initialize the connection using MCPServerStreamableHttp with your Vinkius endpoint URL and pass it to your Agent constructor.

Yes. Your agent can call `list_available_builtin_templates` to discover what layouts are active, and then use `generate_pdf_from_template` to inject your application's raw JSON payload into the chosen template.

The SDK automatically discovers all eight Docamatic tools when you pass the MCP server configuration to the Agent. You can set cacheToolsList=True in your streamable HTTP setup to keep tool discovery fast and avoid extra network roundtrips.

Yes. Your agent can use `generate_pdf_from_html` to render your custom HTML layouts, and then pass those output paths to `merge_multiple_pdfs` to combine them into a single file.

All document payloads, raw HTML string inputs, and generated PDF files are processed within secure V8 sandboxes. Your generation data is transient and wiped from our ephemeral environment as soon as the render job completes.

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