Can I trigger an API campaign for a specific user?

Yes! Use the `trigger_campaign` tool with the Campaign ID and a JSON array of recipient objects (e.g., `[{"external_user_id":"123"}]`).

How do I update a user's custom attribute?

Simply ask the agent to `track_user` and provide the External ID along with the new attributes in JSON format (e.g., `{"favorite_color":"blue"}`).

Does the integration allow permanently deleting a user for GDPR compliance?

Yes. Use the `delete_user` mutation with the user's External ID. This will permanently remove their profile and data from your Braze dashboard.

Braze MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Braze
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Braze through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Braze Assistant",
            instructions=(
                "You help users interact with Braze. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Braze"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Braze MCP Server

Connect your Braze customer engagement platform to any AI agent and orchestrate your marketing automation and user tracking workflows through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Braze through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Braze, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

User Orchestration — Track new user attributes and events, identify anonymous users, or permanently delete user profiles for compliance.
Campaign Management — List all your marketing campaigns, retrieve detailed metadata, and instantly trigger API-based campaign sends to specific users.
Canvas (Journey) Control — List and inspect multi-step Canvases, and trigger users to enter specific Canvas workflows.
Data Export — Programmatically export user profile data by their external IDs.

The Braze MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Braze to OpenAI Agents SDK via MCP

Follow these steps to integrate the Braze MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Braze

Why Use OpenAI Agents SDK with the Braze MCP Server

OpenAI Agents SDK provides unique advantages when paired with Braze through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Braze + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Braze MCP Server delivers measurable value.

Automated workflows: build agents that query Braze, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Braze, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Braze tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Braze to resolve tickets, look up records, and update statuses without human intervention

Braze MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Braze to OpenAI Agents SDK via MCP:

delete_user

Delete a user by external ID

export_user_ids

Export profile data for specific users

get_campaign_details

Get details of a specific campaign

get_canvas_details

Get details of a specific Canvas

identify_user

Identify a user (merge alias to external ID)

list_campaigns

List all campaigns

list_canvases

List all Canvases

track_user

Track user attributes or events

trigger_campaign

Trigger an API-triggered campaign

trigger_canvas

Trigger a Canvas journey

Example Prompts for Braze in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Braze immediately.

"List all active campaigns in Braze."

"Track user 'usr_992' with attribute {'loyalty_tier':'Gold'}."

"List all Canvases configured in the workspace."

Troubleshooting Braze MCP Server with OpenAI Agents SDK

Common issues when connecting Braze to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Braze + OpenAI Agents SDK FAQ

Common questions about integrating Braze MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.