How to Use the Liftoff MCP in LangChain

Q: How do I connect the Liftoff MCP Server to my LangChain agent?

Install langchain-mcp-adapters and use the MultiServerMCPClient pointing to your Vinkius endpoint. Retrieve the tools using client.gettools() and pass them directly to your LangChain agent initializer.

Q: Can my LangChain agent handle large CSV downloads from Liftoff?

Yes, your agent uses downloadreportresults to access the completed CSV data. LangChain handles the raw text stream, allowing your agent to parse the rows or pass them to a downstream file-writer tool.

Q: How does LangChain manage asynchronous report generation in Liftoff?

Your LangChain agent runs a polling loop using getreportstatus after calling requestperformancereport. The agent pauses between steps, checking the status until it returns complete before calling the download tool.

Q: Can I combine these tools with other API tools in LangChain?

Yes, LangChain allows you to mix Liftoff tools like listliftoffcreatives with tools from other servers in the same agent. The agent decides when to pull your creative asset list and when to trigger other actions based on your prompt.

Run multi-step mobile ad reporting chains in LangChain with live Liftoff performance data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Liftoff MCP to LangChain

Create your Vinkius account to connect Liftoff 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 Liftoff with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate multi-step campaign audits in LangChain

The `list_liftoff_campaigns` tool pulls your active ad campaigns directly into your LangChain ReAct agent's context window. Your agent parses this list, identifies underperforming campaigns, and immediately feeds those IDs into `request_performance_report` to spin up a deep-dive analysis. You don't have to manually glue these steps together. LangChain chains the output of the campaign list directly into the report request, letting your agent run the entire sequence based on real-time metadata.

Trace report polling latency with LangSmith

The `get_report_status` tool lets your LangChain agent monitor asynchronous report generation without blocking your main application thread. LangSmith traces the exact latency of each status check, showing you how long the Liftoff API takes to prepare your data. Once the status switches to complete, the agent automatically triggers `download_report_results` to fetch the raw CSV. Each step of this MCP execution pipeline is logged in LangSmith, giving you clear visibility into Liftoff API response times and token costs.

Connect Liftoff MCP Server to your SQL databases

The `get_spend_metrics` tool fetches synchronous performance data that your LangChain agent can instantly join with your internal database records. By combining this MCP server tool with LangChain's SQL database integrations, you can write chains that compare Liftoff spend against your actual backend revenue. Your LangChain agent queries both sources in a single execution loop, calculating true mobile ad ROI without manual Liftoff data exports. This setup turns raw Liftoff performance metrics into structured database updates inside your LangChain application with zero intermediate script writing.

Setup guide

Set up Liftoff 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 Liftoff 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({
    "liftoff-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 Liftoff 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 Liftoff. 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 Liftoff 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 Liftoff MCP in LangChain

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` pointing to your Vinkius endpoint. Retrieve the tools using `client.get_tools()` and pass them directly to your LangChain agent initializer.

Yes, your agent uses `download_report_results` to access the completed CSV data. LangChain handles the raw text stream, allowing your agent to parse the rows or pass them to a downstream file-writer tool.

Your LangChain agent runs a polling loop using `get_report_status` after calling `request_performance_report`. The agent pauses between steps, checking the status until it returns complete before calling the download tool.

Yes, LangChain allows you to mix Liftoff tools like `list_liftoff_creatives` with tools from other servers in the same agent. The agent decides when to pull your creative asset list and when to trigger other actions based on your prompt.

Your mobile advertising performance data and spend metrics flow directly through Vinkius's secure sandboxed connection to your local LangChain execution environment. No ad spend figures or campaign IDs are stored on Vinkius servers, keeping your proprietary marketing data isolated within your own infrastructure.

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