How to Use the Adjust MCP in LangChain

Q: Can my LangChain agent compare two different KPI reports from Adjust?

Yes. You'd design a chain where the agent calls getkpireport twice with different date ranges. It then holds both results in memory to perform the comparison or send them to an analysis model.

Build multi-step attribution agents and marketing workflows with Adjust and LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adjust MCP to LangChain

Create your Vinkius account to connect Adjust 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 Adjust with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check App Configs in Your Chains

The `get_app_settings` tool lets your agent pull the current configuration for any of your apps. This is the starting point for most chains you'll build. Your agent can use the settings data to decide which report to run next or how to format its output. It's a simple, reliable way to make your chains context-aware.

Run Filtered KPI Reports with LangChain

Use the `get_kpi_report` tool to pull performance metrics directly into your LangChain agents. You can filter by date ranges to get just the data you need for a specific task. Your agent can then analyze the report, compare it to previous runs, or pass the results to another tool for summarization. The raw data flows right through your chain, from one step to the next.

Inspect Device Data in an MCP Server

The `inspect_device` tool gives your agent a way to look up attribution details for a specific device ID. It's a direct line into your core attribution data. A chain could use this to investigate an anomaly found in a KPI report, or to build a sequence that checks a device and then updates a record in another system. It's all about connecting the dots.

Setup guide

Set up Adjust 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 Adjust 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({
    "adjust-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 Adjust 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 Adjust. 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 Adjust 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 Adjust MCP in LangChain

Just pass the Adjust tools from the MCP client to your agent. The LangChain agent will decide whether to run `get_kpi_report` after `get_app_settings` based on the goal. LangSmith gives you a full trace of the decisions.

Yes. You'd design a chain where the agent calls `get_kpi_report` twice with different date ranges. It then holds both results in memory to perform the comparison or send them to an analysis model.

Vinkius handles it. You get a single endpoint token that you plug into the `MultiServerMCPClient`. There's no need to manage OAuth or individual API keys for Adjust.

The client is stateless by default, which is good for simple chains. For more complex workflows where you need to remember previous steps, just wrap your calls in the `client.session()` context manager.

Your app settings, KPI reports, and device attribution data are streamed through Vinkius's ephemeral sandboxes. The connection is encrypted, and your token is the only key. No data is stored at rest on the MCP server.

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