How to Use the Nutrient Workflow MCP in OpenAI Agents SDK

Q: How do I connect the Nutrient Workflow MCP Server to the OpenAI Agents SDK?

Install the library using pip install openai-agents first. Initialize the connection using MCPServerStreamableHttp with your Vinkius endpoint, then pass the server object directly into your Agent constructor.

Q: Can my agent start a PDF approval process automatically?

Yes, your agent uses the startrequest tool to launch new processes. It passes the required document metadata to kick off the sequence without human intervention.

Spin up production-grade document approval agents using the OpenAI Agents SDK to sign, annotate, and route PDFs without manual handoffs using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Nutrient Workflow MCP to OpenAI Agents SDK

Create your Vinkius account to connect Nutrient Workflow 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 Nutrient Workflow with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate Document Routing in OpenAI Agents SDK

The `start_request` tool initiates custom document approval workflows directly inside your Python agent pipelines. By hooking this endpoint to your agent, the model triggers multi-stage PDF approvals the second a client uploads a file. You set up the MCP Server connection using the MCPServerStreamableHttp configuration, and the agent handles the rest. This integration bypasses messy glue code, letting your system pass document tasks between specialized agents while maintaining strict execution logs in your OpenAI dashboard.

Resolve and Complete PDF Tasks Safely

The `complete_task` tool updates the status of active document reviews and processes signature steps. Your agent uses this endpoint to sign off on specific stages once the required PDF fields are validated. Because this MCP Server runs inside a zero-trust sandbox, you do not have to worry about untrusted code executing during the approval. The OpenAI platform traces every single action, blocking unauthorized attempts to modify critical document states.

Inspect Pending Tasks and Document States

The `list_user_tasks` and `get_task` tools expose all outstanding document actions that require human or machine intervention. Your agent pulls this list to identify bottlenecks and query specific task details before taking action. Look, here's the thing. Setting `cacheToolsList=True` ensures your agent retrieves these task lists instantly, avoiding redundant network roundtrips and letting the model make fast routing decisions based on real-time task queues.

Setup guide

Set up Nutrient Workflow 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 Nutrient Workflow tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the library using `pip install openai-agents` first. Initialize the connection using `MCPServerStreamableHttp` with your Vinkius endpoint, then pass the server object directly into your Agent constructor.

Yes, your agent uses the `start_request` tool to launch new processes. It passes the required document metadata to kick off the sequence without human intervention.

The SDK automatically inspects the Vinkius endpoint and registers all 10 document tools at runtime. You do not need to write manual schemas or map endpoints yourself.

You control access by configuring the agent's system instructions or limiting the exposed tools in your constructor. This prevents the agent from calling administrative endpoints like `list_users` if it only needs to sign files.

Your document files and workflow states are processed within an ephemeral V8 Isolate sandbox on Vinkius using our secure MCP setup. No data is stored permanently on the host, and all traffic is encrypted end-to-end to ensure compliance with strict IT policies.

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