How to Use the Braze MCP in LangChain

Q: How does LangChain handle errors when updating Braze profiles?

If a tool call like trackuser fails, the exception is passed back into the LangChain run loop. Your agent can catch this error, inspect the payload, and attempt to resolve it or log the issue.

Run Braze campaigns and manage user profiles directly from your LangChain multi-step reasoning chains.

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 LangChain

Create your Vinkius account to connect Braze to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Braze actions with LangChain agents

The Braze MCP Server turns your marketing engine into a suite of tools your LangChain agent can call in sequence. By combining `list_campaigns` and `trigger_campaign`, your agent inspects active marketing runs and launches them based on real-time database changes. You get full visibility into this execution chain. LangSmith logs every single tool call, showing you exactly when your agent decided to call `track_user` or pull details via `get_campaign_details`.

Automate user lifecycle events in LangChain

This MCP Server exposes direct endpoints to modify your customer profiles without leaving your Python script. Your agent can run `identify_user` to merge user aliases and then immediately execute `track_user` to update custom attributes based on chat interactions. Instead of writing custom API wrappers, you plug these tools directly into your LangGraph setup. The agent handles user lookup via `export_user_ids` and decides whether to trigger a custom journey.

Run and monitor multi-step Canvas journeys

The Braze integration lets you monitor and run complex user journeys by letting your agent query and launch Canvases. Your agent uses `list_canvases` to find active workflows and `trigger_canvas` to push specific users into targeted onboarding paths. You can inspect the exact configuration of any journey first. The agent calls `get_canvas_details` to verify the entry steps before executing the trigger, preventing accidental messaging.

Setup guide

Set up Braze MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Braze tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "braze-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Braze transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You install the langchain-mcp-adapters package and initialize the MultiServerMCPClient with the Vinkius endpoint. From there, call client.get_tools() and pass the resulting list directly into your LangChain agent constructor.

Yes, the agent evaluates intermediate chain steps to determine if it should run `trigger_campaign`. It uses the parameters returned from previous database queries to populate the payload.

If a tool call like `track_user` fails, the exception is passed back into the LangChain run loop. Your agent can catch this error, inspect the payload, and attempt to resolve it or log the issue.

Yes. You can load these MCP tools into a LangGraph state utility. This allows your state machine to pass user IDs across different nodes before calling `delete_user` or `identify_user`.

Vinkius runs the MCP server in an isolated, ephemeral V8 sandbox, meaning no customer profiles or API keys are written to persistent storage. All data passing through tools like `export_user_ids` is encrypted in transit and discarded immediately after the tool execution 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