How to Use the Adikteev MCP in LangChain

Q: How do I get started with Adikteev and LangChain?

First, pip install the MCP adapter and point it to your Vinkius server URL. Then, call client.gettools() to load the Adikteev functions and pass that list into your agent's constructor. Your agent now has access to all five Adikteev tools.

Q: Can my LangChain agent create a new Adikteev segment from churn scores?

Yes, that’s a perfect use case. Your agent can call getchurnscores, process the results in code to identify at-risk users, and then pass that user list to the createsegment tool. This creates a dynamic retargeting audience right in your Adikteev account.

Q: What kind of reports can I get from Adikteev with LangChain?

The getreporting tool pulls your campaign performance data. You can ask your agent something like, "Pull the performance report for last week's iOS campaign," and it will use the tool to get the numbers you need from Adikteev.

Build LangChain agents that automatically manage Adikteev segments and pull campaign reports in a single, observable chain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adikteev MCP to LangChain

Create your Vinkius account to connect Adikteev 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 Adikteev with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Audience Management

This toolset gives your LangChain agent the ability to create and manage Adikteev audience segments directly. Your agent can `list_segments` to see what's already there, then use `create_segment` to build a new one based on criteria you define, like users who are at risk of churning. Because it's LangChain, you can chain these actions together. An agent could check if a 'High-Value Lapsed Users' segment exists, and if not, create it on the fly before moving to the next step. You can watch the whole sequence happen in LangSmith, step by step.

Connect Churn Data to Campaign ROI

Get user churn predictions and campaign performance data right into your agents. The `get_churn_scores` tool pulls a risk score for each user, while `get_reporting` grabs the raw numbers on how your campaigns are performing. This is where chaining gets powerful. A smart agent can pull churn scores, find the at-risk users, create a new Adikteev segment for them, and then trigger a re-engagement campaign—all without manual intervention. It’s not just data retrieval; it's automated action based on that data.

Build Adikteev Tools into LangChain Agents

This MCP Server gives your LangChain agents five specific tools for talking to the Adikteev platform. You get functions for listing your company ID, managing audience segments, checking churn scores, and pulling campaign performance reports. Setup is simple. You install the adapter, point it to the Vinkius endpoint, and the tools are ready to pass to your agent. LangChain's ReAct logic lets the agent figure out which Adikteev tool to use and in what order to accomplish the goal you gave it.

Setup guide

Set up Adikteev 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 Adikteev 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({
    "adikteev-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 Adikteev 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 Adikteev. 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 Adikteev 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 Adikteev MCP in LangChain

First, `pip install` the MCP adapter and point it to your Vinkius server URL. Then, call `client.get_tools()` to load the Adikteev functions and pass that list into your agent's constructor. Your agent now has access to all five Adikteev tools.

Yes, that’s a perfect use case. Your agent can call `get_churn_scores`, process the results in code to identify at-risk users, and then pass that user list to the `create_segment` tool. This creates a dynamic retargeting audience right in your Adikteev account.

The `get_reporting` tool pulls your campaign performance data. You can ask your agent something like, "Pull the performance report for last week's iOS campaign," and it will use the tool to get the numbers you need from Adikteev.

Absolutely. Every call to an Adikteev tool your LangChain agent makes is automatically traced in LangSmith. You'll see the exact inputs, outputs, latency, and token count for each step, which makes debugging your marketing automation chains much simpler.

Yes. Your campaign performance data and audience segment details are streamed through Vinkius's ephemeral, zero-trust environment. This MCP server doesn't store your data; it just proxies requests to Adikteev using your authenticated token, and the connection is torn down afterward.

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