How to Use the Digital Turbine MCP in AutoGen

Enable AutoGen agents to debate and decide on mobile growth strategies using live Digital Turbine data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Digital Turbine MCP to AutoGen

Create your Vinkius account to connect Digital Turbine 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 Digital Turbine with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate growth strategies with live data

Your agents use `list_growth_campaigns` to gather data for their internal discussions. One agent flags low-performing channels while another proposes reallocating budget, forcing a consensus based on hard numbers. This removes bias from your decision-making. The agents reach a conclusion only after they cross-reference the data from your account.

Automated performance monitoring via debate

Assign an agent to call `get_performance_summary` on a schedule. If the metrics drop, the agent alerts the team or initiates a secondary search for high-engagement alternatives using `list_high_engagement_campaigns`. Your agents act as a team of analysts. They collaborate to ensure your campaigns perform well without requiring constant manual intervention.

Secure multi-agent monetization auditing

Deploy a security agent to check `get_app_monetization_details` while a finance agent tracks revenue through `get_revenue_report`. They negotiate to ensure that monetization settings remain compliant with your revenue targets. This setup provides a layer of checks and balances. The agents challenge each other to verify that every configuration change is justified by the data.

Setup guide

Set up Digital Turbine 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 Digital Turbine 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="Digital Turbine_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Digital Turbine 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="Digital Turbine_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Digital Turbine 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 Digital Turbine. 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 Digital Turbine 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 Digital Turbine MCP in AutoGen

You pass the MCP tool adapter to your AssistantAgent constructor. This automatically maps the API schema so your agents can call the tools within their conversation flow.

Yes, the tools are shared across your agent group. This allows different specialized agents to access the same API data for their collaborative discussions.

All communication happens through an ephemeral, zero-trust sandbox. The server only returns the data requested by the agent, keeping your account details isolated from the wider system.

The agents detect the inconsistency and discuss the issue. They can decide to re-run the query or escalate the problem to you if the data remains ambiguous.

You control which tools the agents have access to by filtering the tool list before passing it to the agent constructor. This restricts the scope of their actions to exactly what you permit.

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