How to Use the eSputnik MCP in LangChain

Q: How do I build a welcome sequence for new users with eSputnik and LangChain?

Your LangChain agent can use the createcontact tool, then immediately pipe that contact's ID into the attachtogroup tool for your 'New Users' segment. This segment can be linked to an automated welcome campaign inside eSputnik.

Q: How should a LangChain agent handle unsubscribes in eSputnik?

Before any sendsmartsend or attachtogroup action, your agent's chain should include a call to listunsubscribed. It can then check if the target contact is on that list, ensuring you don't message people who have opted out.

Build marketing automation chains that run themselves. Connect your LangChain agent to eSputnik and let it handle the details.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect eSputnik MCP to LangChain

Create your Vinkius account to connect eSputnik 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 eSputnik with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Your Customer Segmentation

This MCP server gives your agent the tools to build and execute complex segmentation logic. It's not just about sending an email. It's about your agent deciding who gets it and why, in real time. Your agent can start by using `list_groups` to understand existing segments, then use `search_contacts` to find users matching new criteria. The output from that search feeds directly into `attach_to_group`, creating a dynamic audience. This isn't a pre-canned workflow; it's a reasoning chain your agent builds on the fly.

Automate Contact Lifecycle Management

Use this server to build agents that manage your contact database. When a new user signs up, a LangChain agent can immediately `create_contact` in eSputnik, no human intervention needed. It's a direct connection from your system to your marketing platform. From there, the agent can use logic to `attach_to_group` for a welcome sequence. If a contact needs to be moved, the agent can `detach_from_group` and add them to another. The entire contact journey, from creation to segmentation, becomes a single, observable chain of tool calls.

Build Responsive Workflows with Your LangChain MCP Server

Connect your internal systems to eSputnik's automation engine. An agent can use `trigger_event` to kick off a pre-built workflow in eSputnik when something happens in your app, like a user upgrading their plan. After triggering the event, the agent can wait and then check on the results. It uses `get_message_status` to confirm that the welcome email was delivered. If not, it can try a different channel or flag it for review. This creates a closed-loop system that doesn't just send—it confirms.

Setup guide

Set up eSputnik 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 eSputnik 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({
    "esputnik-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 eSputnik 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 eSputnik. 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 eSputnik 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 eSputnik MCP in LangChain

Your LangChain agent can use the `create_contact` tool, then immediately pipe that contact's ID into the `attach_to_group` tool for your 'New Users' segment. This segment can be linked to an automated welcome campaign inside eSputnik.

Yes. You'd build a chain that reads from your CRM's API, then uses the `search_contacts` tool to see if the contact exists in eSputnik. If not, it calls `create_contact`; if so, it updates them. It's a classic ETL job, but run by an agent.

Before any `send_smart_send` or `attach_to_group` action, your agent's chain should include a call to `list_unsubscribed`. It can then check if the target contact is on that list, ensuring you don't message people who have opted out.

Use a tracer like LangSmith. Every call your agent makes to the eSputnik MCP server, from the tool inputs to the final outputs, is logged. You can see exactly what `get_contact` returned or why `trigger_event` failed.

The server only handles contact data like emails and phone numbers for the duration of the API call. Vinkius runs each tool call in an ephemeral, sandboxed environment. Your connection is secured by a unique token, and no contact data is stored on the MCP server itself.

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