How to Use the Novu MCP in OpenAI Agents SDK

Q: Can I use OpenAI Agents SDK to manage Novu subscriber preferences in bulk?

Yes, you can pass the bulkupdatesubscriberpreferences tool directly to your agent. The agent processes the user's natural language request, maps it to the required JSON schema, and updates multiple channels in one execution.

Q: How does OpenAI Agents SDK handle tracing for Novu workflow triggers?

Every time your agent invokes triggerevent or canceltrigger, the payload and tool response are logged in the OpenAI developer dashboard. This gives you a clear audit trail of exactly what data the agent sent to your notification backend.

Q: Can the agent verify which communication channels are active?

Yes, the agent uses listactiveintegrations to check your current delivery channels. It can check if your SMS or email providers are online before attempting to send a message.

Run production-ready notification pipelines using the OpenAI Agents SDK to trigger Novu workflows and manage subscriber preferences.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Novu MCP to OpenAI Agents SDK

Create your Vinkius account to connect Novu 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 Novu with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe Novu triggers with OpenAI Agents SDK

Your OpenAI Agents SDK pipeline can safely route transactional alerts across email, SMS, and push channels without manual coding. By feeding the Novu MCP Server tools directly into your agent stream, the model decides when to run `trigger_event` or `trigger_bulk_event` based on live user events. Because OpenAI Agents SDK supports strict schema validation, you do not have to worry about the model passing malformed JSON to your Novu backend. If a user cancels an action, the agent invokes `cancel_trigger` to halt the pending queue instantly before any message leaves the server.

Dynamic subscriber provisioning and preference management

Stop writing custom code to sync user profiles with your Novu notification engine. Your OpenAI Agents SDK setup handles this on the fly by calling `create_subscriber` or `update_subscriber` whenever a user changes their settings. When users want to opt out of specific channels, the agent executes `bulk_update_subscriber_preferences` to update their profile. This keeps your Novu integration compliant with user communication preferences automatically, backed by OpenAI's native guardrails that prevent unauthorized preference changes.

Automated layout and workflow creation

Let your OpenAI Agents SDK configuration build and modify your actual Novu templates and structures. By exposing `create_layout` and `create_workflow` to your agent, your product team can describe a new notification campaign in plain English and let the model configure the backend. This setup completely bypasses the usual engineering bottleneck for transactional emails. The agent sets up the Novu rules, links them to the correct templates, and tests the integration using `list_active_integrations` to ensure everything is configured properly before going live.

Setup guide

Set up Novu 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 Novu tools at runtime.
3

Create your Agent

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

Run the agent

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

You should configure the OpenAI Agents SDK with backoff handlers around the `trigger_event` tool calls. If Novu returns a rate limit response, the SDK's built-in tracing will flag the error, letting your agent pause and retry the execution stream safely.

Yes, you can pass the `bulk_update_subscriber_preferences` tool directly to your agent. The agent processes the user's natural language request, maps it to the required JSON schema, and updates multiple channels in one execution.

Every time your agent invokes `trigger_event` or `cancel_trigger`, the payload and tool response are logged in the OpenAI developer dashboard. This gives you a clear audit trail of exactly what data the agent sent to your notification backend.

Yes, the agent uses `list_active_integrations` to check your current delivery channels. It can check if your SMS or email providers are online before attempting to send a message.

All subscriber phone numbers and email addresses processed by `create_subscriber` are sent over TLS directly to your Novu instance. Vinkius runs the server in an ephemeral sandbox, meaning no personal contact details are ever written to persistent disk storage during the tool execution.

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