How to Use the Bloomreach MCP in LangChain

Q: How do I pass Bloomreach catalog data to a LangChain agent?

You register the listcatalogs tool within your LangChain tool list and let the agent call it dynamically. The agent receives the raw catalog list and passes the selected catalog ID directly to getcatalogitems in the next step of the chain.

Q: Can I trace Bloomreach tool execution latencies in LangChain?

Yes, every call to tools like listcampaigns is tracked automatically if you have LangSmith enabled. You will see the precise execution time and payload sizes for each MCP Server request in your trace timeline.

Build multi-step marketing workflows using LangChain to query Bloomreach customer segments and catalogs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bloomreach MCP to LangChain

Create your Vinkius account to connect Bloomreach 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 Bloomreach with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Bloomreach data directly into LangChain agents

LangChain agents execute real-time marketing audits by running `list_campaigns` and passing the raw campaign IDs directly to subsequent analysis chains. You construct chains where the output of your campaign list feeds into LLM evaluation steps without manual data shifting. By combining this MCP Server with LangChain's memory, your agent tracks previous runs to spot inactive marketing setups. The agent identifies dead campaigns and immediately queries `list_webhooks` to verify if external notifications are still firing.

Map customer traits with LangChain state machines

The `list_attributes` tool feeds customer metadata directly into LangChain's structured output parsers for instant profiling. Your agent reads these attributes, filters them based on active LangChain memory, and then runs `get_customer_properties` to build a complete profile. This setup eliminates manual data extraction when debugging user profiles during live LangChain runs. You get raw JSON properties formatted instantly for your agent's next logical decision.

Inspect Bloomreach segments inside LangSmith traces

Every call to `list_segments` or `list_segmentations` appears as a distinct, traceable step inside your LangSmith dashboard. You see the exact latency, payload size, and response times of your segment queries within your active LangChain pipeline. Debugging failing runs becomes fast because you can isolate whether an empty segment list or a slow network call broke the chain. Your agent uses this trace data to handle empty arrays gracefully before executing the next tool.

Setup guide

Set up Bloomreach 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 Bloomreach 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({
    "bloomreach-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 Bloomreach 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 Bloomreach. 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 Bloomreach 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 Bloomreach MCP in LangChain

You register the `list_catalogs` tool within your LangChain tool list and let the agent call it dynamically. The agent receives the raw catalog list and passes the selected catalog ID directly to `get_catalog_items` in the next step of the chain.

Yes, every call to tools like `list_campaigns` is tracked automatically if you have LangSmith enabled. You will see the precise execution time and payload sizes for each MCP Server request in your trace timeline.

Your LangChain agent receives the empty array directly from `list_segments` and uses its internal reasoning loop to decide the next step. You can write a prompt template that instructs the agent to halt or try a different segmentation tool if no data returns.

Yes, you can combine this MCP Server with other endpoints inside a single LangChain agent. The agent selects whether to query marketing data here or pull product details from a separate database server.

This MCP Server runs inside a secure, ephemeral Vinkius sandbox that handles authentication locally. Your raw customer properties retrieved via `get_customer_properties` pass directly to your local LangChain runtime without being stored or logged on our servers.

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