How to Use the Adjust MCP in AutoGen

Q: How do AutoGen agents decide which Adjust tool to use?

You assign the tools to an agent, usually an AssistantAgent. The agents then discuss the user's request, and one will propose using a tool like getkpireport. Other agents can agree or suggest a different approach.

Q: What's the easiest way to connect Adjust to my AutoGen setup?

Use the mcpservertools function from the autogen-ext library. Just give it your Vinkius server URL, and it returns a list of tools ready to be passed to your AssistantAgent.

Q: Do I need to write custom tool schemas for this to work?

No. The McpToolAdapter handles the conversion from the MCP standard to the format AutoGen expects. Your agents get fully-functional Python tools without any manual schema work.

Let multiple AI agents debate your Adjust attribution data with Microsoft AutoGen.

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 AutoGen

Create your Vinkius account to connect Adjust 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 Adjust with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Have Agents Discuss App Settings

One agent can use `get_app_settings` to fetch your Adjust app's configuration. It can then present this information to other agents in the group chat. A 'ComplianceAgent' could check the settings for privacy flags while a 'GrowthAgent' looks for new tracking opportunities. They debate the findings before recommending a change.

Multi-Agent KPI Analysis with an MCP Server

An agent runs `get_kpi_report` and shares the results with the group. This single action kicks off a conversation. Your 'AnalystAgent' might spot a drop in installs, but the 'MarketingAgent' could point out it corresponds with a planned budget shift. AutoGen lets them argue and converge on a real explanation.

Investigate Attribution with a Team of Agents

The `inspect_device` tool lets an agent pull up a device's attribution record. This isn't just a simple lookup; it's evidence for a discussion. One agent might flag a device for potential fraud. Another agent can then use the same tool to pull data on related devices, building a case together before alerting a human.

Setup guide

Set up Adjust 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 Adjust 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="Adjust_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent Adjust 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 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 AutoGen

You assign the tools to an agent, usually an `AssistantAgent`. The agents then discuss the user's request, and one will propose using a tool like `get_kpi_report`. Other agents can agree or suggest a different approach.

Absolutely. You can create a 'Reporter' agent with access to the Adjust tools and a separate 'Executor' agent that can't. The Reporter provides the data, and the Executor decides what to do based on the group's conversation.

Use the `mcp_server_tools` function from the `autogen-ext` library. Just give it your Vinkius server URL, and it returns a list of tools ready to be passed to your `AssistantAgent`.

No. The `McpToolAdapter` handles the conversion from the MCP standard to the format AutoGen expects. Your agents get fully-functional Python tools without any manual schema work.

The Adjust MCP server processes requests for app settings and KPI reports in an isolated environment. The data is sent only to the specific AutoGen agent that requested it. It's up to you how that agent shares the information with other agents in the conversation.

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