How to Use the Braze MCP in OpenAI Agents SDK

Q: Can I trace Braze user updates made by OpenAI Agents SDK?

Yes, every call to trackuser or identifyuser shows up in your OpenAI dashboard with full input and output payloads. This lets you debug exactly what attributes your agent sent to the marketing platform.

Run safe, production-grade Braze campaigns and user tracking directly from your OpenAI Agents SDK pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Braze MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Braze campaign triggers in OpenAI Agents SDK

The `trigger_campaign` tool fires off API-triggered campaigns, while `trigger_canvas` kicks off multi-step customer journeys. By hooking these tools directly into your OpenAI Agents SDK setup, you run automated marketing steps with built-in system guardrails that verify parameters before any external API calls execute. Your agent checks campaign details first to ensure the target audience matches, preventing accidental mass-messaging. If a run doesn't meet your pre-defined safety rules, the SDK blocks the action and logs the event to your OpenAI dashboard instantly.

Safe profile updates using this MCP Server

The `track_user` tool logs custom attributes and events to customer profiles, and `identify_user` links anonymous aliases to permanent external IDs. This MCP Server gives your OpenAI Agents SDK the exact endpoints needed to clean up and update your marketing database during conversation flows. Because production environments require strict data handling, you can use the SDK's agent handoff feature to pass sensitive tasks to a specialized user-data agent. This dedicated agent handles the `delete_user` tool exclusively, keeping customer deletion logic separated from conversational agents.

Inspect Braze journeys inside OpenAI Agents SDK

The `list_campaigns` tool pulls active marketing campaigns, while `get_campaign_details` and `get_canvas_details` extract live metadata about your active customer journeys. Your OpenAI Agents SDK uses these tools to read live campaign states before making decisions on what message to trigger next. Instead of hardcoding journey IDs, the agent queries the list of active canvases to find the correct identifier dynamically. All of these discovery queries show up in your OpenAI tracing dashboard when using the MCP Server, so you can audit exactly what campaign data your agent read before it took action.

Setup guide

Set up Braze 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 Braze tools at runtime.
3

Create your Agent

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

Run the agent

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

You set rate limits directly on the agent's tool execution loop. When calling `trigger_campaign`, the SDK handles the API response and lets you write logic to pause or queue further triggers if Braze returns a rate-limit error.

Yes, every call to `track_user` or `identify_user` shows up in your OpenAI dashboard with full input and output payloads. This lets you debug exactly what attributes your agent sent to the marketing platform.

Vinkius manages the API keys securely in a zero-trust sandbox. Your OpenAI Agents SDK only needs the single endpoint token to execute tools like `list_canvases` or `trigger_canvas`.

You can assign all 10 tools to a single agent, but OpenAI Agents SDK works best when you split them. We recommend one agent for reading data with `list_campaigns` and a separate, restricted agent for executing `trigger_canvas`.

The server processes user IDs, attributes, and event logs through ephemeral V8 isolates. No customer profile data or tracking history is stored on Vinkius, ensuring your user identifiers remain strictly within your OpenAI Agents SDK runtime and the marketing platform.

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