How to Use the Emarsys MCP in LangChain

Get raw Emarsys marketing data directly into your LangChain chains to automate campaign audits and segment checks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Emarsys MCP to LangChain

Create your Vinkius account to connect Emarsys 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 Emarsys with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Emarsys campaigns in LangChain chains

The `quick_engagement_volume_audit` tool pulls high-level marketing volumes directly into your LangChain run, letting your agent inspect active performance metrics before deciding on the next step. This MCP Server lets your agent inspect active performance metrics without you writing custom API parsing scripts. By feeding these metrics directly into downstream LangChain prompts, you build self-correcting loops that flag anomalies in real time. The agent handles the data extraction and formatting, passing the output straight to your evaluation templates.

Map Emarsys segments to LangChain agent decisions

The `list_audience_segments` tool exposes your entire Emarsys segment architecture directly to LangChain ReAct agents. Your agent reads the current active filters, compares them against incoming lead behavior, and determines which segment requires immediate targeting adjustments. This setup removes the manual step of exporting contact filters to check list sizes. The LangChain agent queries the active segments, processes the JSON payload, and routes the next execution step based on actual live audience sizes.

Track Emarsys automation paths with this MCP Server

The `list_automation_programs` tool exposes active marketing journeys to your LangChain routing chains. Your agent inspects running workflows, checks their configurations, and maps out where a customer might get stuck in a multi-step sequence. Combining this with LangSmith tracing gives you a clear view of how your MCP Server calls behave during complex, multi-turn routing sessions. You see exactly what tools were called and what parameters were passed to the API.

Setup guide

Set up Emarsys 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 Emarsys 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({
    "emarsys-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 Emarsys 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 Emarsys. 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 Emarsys 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 Emarsys MCP in LangChain

Instantiate MultiServerMCPClient with the Vinkius HTTP endpoint, then pass the tools from client.get_tools() to your LangChain agent. This gives your agent immediate access to tools like list_email_campaigns and get_campaign_details in its execution loop.

Yes, your LangChain agent resolves multi-step tasks by chaining tools like list_trigger_events and list_automation_programs in sequence. The agent analyzes the output of one tool to determine the parameters for the next call without manual intervention.

Use LangSmith tracing to monitor every call your LangChain agent makes to the Emarsys tools like quick_engagement_volume_audit. You get full visibility into payload structures, latency, and token consumption for every API request.

You can register this MCP server alongside others in a single LangChain client configuration. The agent dynamically chooses whether to call list_marketing_contact_lists or query external databases based on the user's prompt.

This server accesses email campaign metadata, contact list structures, and automation program configurations. Vinkius processes these requests inside secure, ephemeral V8 isolates, ensuring your marketing structures and list IDs are never stored or exposed to external networks.

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