How to Use the AppLovin MCP in AutoGen

Q: How do I give AppLovin tools to my AutoGen agents?

You use the mcpservertools function from the autogen-extmcp package. Just provide your MCP server URL. It returns a list of tools you can assign to any AssistantAgent in your group.

Let AutoGen agents debate and manage your AppLovin ad strategy.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AppLovin MCP to AutoGen

Create your Vinkius account to connect AppLovin to AutoGen 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 AppLovin with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Specialist Ad Agents

The AppLovin tools let you build a team of collaborating agents. Create a "Monetization" agent that only has access to `get_max_report` and `get_max_cohort_report`. Then, create a "UA" agent that uses `list_campaigns` and `get_app_discovery_report`. Set them a goal, and they'll start a conversation. The Monetization agent can report on revenue changes, while the UA agent discusses which campaigns might be responsible. They work together, each using their own specialized tools.

Debate Performance Metrics

AutoGen's strength is multi-agent debate. One agent might pull user-level data with `get_user_ad_revenue_report` and argue that a campaign is successful based on high-value users. Another agent can use `get_app_discovery_report` to counter that the campaign's overall impression volume is too low. This isn't a simple script; it's a negotiation. The agents challenge each other's findings, request more data, and work toward a consensus on how to interpret your AppLovin performance. You're building a system that reasons through ambiguity.

Automate Actions with an MCP Server

Start the conversation with a simple prompt, like "Summarize last week's MAX performance." An agent will use `get_max_report` to pull the data. Based on the results, another agent can propose a follow-up action, like digging into a specific app's cohort data with `get_max_cohort_report`. This MCP Server provides the building blocks for your agent group. AutoGen provides the conversational framework. Together, they let you build systems that don't just report on data, but discuss its implications and decide what to do next.

Setup guide

Set up AppLovin MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes AppLovin tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="AppLovin_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent AppLovin data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="AppLovin_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent AppLovin data")
    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 AppLovin. 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 AppLovin 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 AppLovin MCP in AutoGen

You use the `mcp_server_tools` function from the `autogen-ext[mcp]` package. Just provide your MCP server URL. It returns a list of tools you can assign to any `AssistantAgent` in your group.

Yes. You can fetch the full list of tools from the AppLovin MCP server, then manually create smaller lists and assign them to each agent. This lets you create specialists, like a "read-only" analyst agent and a "campaign manager" agent.

In an AutoGen conversation, one agent might suggest a course of action, and another agent with the right tools will execute it. The decision comes from the dialogue. For example, a "Planner" agent might tell a "Worker" agent to call `get_max_report` with a specific date range.

Yes. The conversation transcript shows everything. You'll see one agent calling a tool like `list_apps` and then posting the raw output back into the chat for other agents to see and use.

The data, which includes your advertising metrics, is retrieved through a secure, isolated Vinkius connection for each tool call. Within AutoGen, this data is part of the conversation context. You are responsible for securing the environment where your agents are running and conversing.

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