How to Use the Aimtell MCP in LangChain

Q: How do I pass Aimtell subscriber attributes from a LangChain run?

You pass the subscriber ID and attributes directly to the addsubscriberattribute tool inside your chain. The agent handles the JSON formatting and updates the profile instantly.

Q: Can a LangChain agent trigger automated Aimtell campaigns?

Yes. The agent uses listapicampaigns to find the target campaign ID, then executes the trigger based on your chain logic. You get full visibility into the execution via LangSmith tracing.

Q: Does the Aimtell MCP integration support LangChain memory?

It does. You can store subscriber details retrieved via getsubscriberdetails in your agent's memory to personalize subsequent push notifications in the same session.

Q: How do I filter active subscriber segments?

Your agent uses the MCP Server tool listsegments to retrieve all defined target groups. It then filters the results programmatically to select the correct audience for your next push dispatch.

Run multi-step push notification campaigns and update subscriber segments directly inside your LangChain reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aimtell MCP to LangChain

Create your Vinkius account to connect Aimtell 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 Aimtell with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Aimtell push alerts with LangChain agents

Your LangChain agent uses this MCP tool to call `send_one_off_notification` when external conditions trigger a run. The tool immediately sends the push payload to your target audience. You don't write glue code; the agent reads the tool schema and executes the dispatch. Next, the agent uses `get_campaign_performance` to fetch click-through rates. LangSmith traces the entire sequence, mapping latency and token costs for every API call in the chain.

Dynamic subscriber tagging via LangChain chains

This MCP Server lets your agent run `add_subscriber_attribute` to update user profiles based on conversation logs. The agent extracts user preferences from a chat history and updates the Aimtell subscriber record on the fly. You chain this with `get_subscriber_details` to verify the new attributes took hold. This turns static push notifications into personalized, behavioral triggers without manual intervention.

Automated campaign audits in LangChain

The agent connects to the MCP Server to call `list_campaigns` and `list_triggered_campaigns` to audit your active notifications. It compares active templates against your vector database to flag outdated copy. It then pulls segment data via `list_segments` to verify targeting parameters. You get a complete, automated audit of your push marketing setup in a single run.

Setup guide

Set up Aimtell 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 Aimtell 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({
    "aimtell-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 Aimtell 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 Aimtell. 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 Aimtell 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 Aimtell MCP in LangChain

You pass the subscriber ID and attributes directly to the `add_subscriber_attribute` tool inside your chain. The agent handles the JSON formatting and updates the profile instantly.

Yes. The agent uses `list_api_campaigns` to find the target campaign ID, then executes the trigger based on your chain logic. You get full visibility into the execution via LangSmith tracing.

It does. You can store subscriber details retrieved via `get_subscriber_details` in your agent's memory to personalize subsequent push notifications in the same session.

Your agent uses the MCP Server tool `list_segments` to retrieve all defined target groups. It then filters the results programmatically to select the correct audience for your next push dispatch.

Vinkius runs the server inside an ephemeral, zero-trust V8 Isolate sandbox. Your subscriber push tokens and custom attributes are never stored or logged on our infrastructure, ensuring complete data isolation.

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