How to Use the Liftoff MCP in LlamaIndex

Q: How do I initialize the Liftoff MCP Server in LlamaIndex?

Install llama-index-tools-mcp and initialize the BasicMCPClient with your Vinkius URL. Wrap it in a McpToolSpec and call totoollistasync to pass the tools to your LlamaIndex agent.

Q: Can LlamaIndex index live spend metrics from Liftoff?

Yes, LlamaIndex calls getspendmetrics to retrieve synchronous performance data and parses the JSON payload directly into document nodes. These nodes are then indexed into your vector store for real-time querying.

Q: How does LlamaIndex handle Liftoff report generation lag?

Your LlamaIndex agent uses requestperformancereport to start the generation, then periodically calls getreportstatus. Once the status is complete, it triggers the download tool and indexes the fresh CSV data.

Q: Can I limit which MCP tools my LlamaIndex agent can use?

Yes, you can use the allowedtools filter in LlamaIndex to restrict the agent's access. For example, you can limit it to listliftoffapps if you only want the agent to read application metadata.

Index your Liftoff mobile ad data into LlamaIndex vector stores for natural language querying.

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 LlamaIndex

Create your Vinkius account to connect Liftoff to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Liftoff campaign metadata for semantic search

The `list_liftoff_campaigns` tool retrieves your active advertising campaigns so LlamaIndex can convert the metadata into vector embeddings. Instead of writing complex SQL queries, you search your Liftoff campaign structure using plain English queries inside your LlamaIndex RAG pipeline. LlamaIndex stores these Liftoff campaign documents in your vector database, making it easy to retrieve specific campaign IDs when you need to run performance checks. This bridges the gap between unstructured questions and structured mobile ad metadata.

Build a queryable base of Liftoff creatives with MCP

The `list_liftoff_creatives` tool pulls your active ad assets directly into LlamaIndex's indexing engine. You can index Liftoff creative names and associations, allowing your LlamaIndex agent to answer questions about which assets are deployed where. By combining this MCP Server with a local vector store, you can query your Liftoff creative inventory inside LlamaIndex without hitting the API endpoints repeatedly. This speeds up your LlamaIndex search operations and keeps your Liftoff API token usage low.

Run RAG on Liftoff performance reports in LlamaIndex

The `download_report_results` tool fetches the raw CSV data of your completed reports, which LlamaIndex instantly parses into queryable text chunks. Your LlamaIndex RAG agent reads these performance chunks to answer complex questions about your Liftoff mobile ad metrics. Instead of staring at massive spreadsheets, you ask LlamaIndex for specific trends, and it extracts the exact rows from the downloaded Liftoff report. LlamaIndex grounds each answer in the actual CSV data retrieved from the Liftoff API.

Setup guide

Set up Liftoff MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Liftoff MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Liftoff tools.",
)
response = await agent.run("List recent Liftoff data")

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 LlamaIndex

Install `llama-index-tools-mcp` and initialize the `BasicMCPClient` with your Vinkius URL. Wrap it in a `McpToolSpec` and call `to_tool_list_async` to pass the tools to your LlamaIndex agent.

Yes, LlamaIndex calls `get_spend_metrics` to retrieve synchronous performance data and parses the JSON payload directly into document nodes. These nodes are then indexed into your vector store for real-time querying.

Your LlamaIndex agent uses `request_performance_report` to start the generation, then periodically calls `get_report_status`. Once the status is complete, it triggers the download tool and indexes the fresh CSV data.

Yes, you can use the `allowed_tools` filter in LlamaIndex to restrict the agent's access. For example, you can limit it to `list_liftoff_apps` if you only want the agent to read application metadata.

Your Liftoff campaign spend metrics and performance data remain inside your local LlamaIndex vector store and memory buffers. Vinkius operates an ephemeral, zero-trust sandbox that handles the API authentication token securely without logging your sensitive financial reports.

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