How to Use the AdsWizz MCP in AutoGen

Q: How do I give my AutoGen assistant access to the AdsWizz tools?

Use the mcpservertools function from the autogen-ext package. Pass it your Vinkius server URL, and it returns a list of tools. You can then assign this tool list to your AssistantAgent during its setup.

Equip your AutoGen agent teams with AdsWizz tools to debate and decide on audio advertising strategy.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdsWizz MCP to AutoGen

Create your Vinkius account to connect AdsWizz 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 AdsWizz with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Arm Your Agents for Strategy Debates

Create a 'Performance Analyst' agent in your group chat. Give it the `get_audio_performance` tool. When another agent asks about a campaign, the analyst pulls the hard numbers and presents them as facts. The AdsWizz tools provide the ground truth for the conversation. A 'Creative Strategist' agent can propose new ideas, but its plans are immediately checked against the real-world data supplied by the analyst agent. This makes the entire discussion more productive.

Automate Campaign Reporting with a Team

Build a simple reporting team. A 'Junior Analyst' agent runs `list_campaigns` and `get_campaign` to gather raw data on all active campaigns, posting the findings to the group chat. A 'Senior Analyst' agent then reads that data, summarizes the key insights, and passes its summary to a 'Writer' agent to format a clean report. The AdsWizz tools are the first step in a multi-agent workflow that mimics a real team.

An MCP Server for Multi-Agent Consensus

One agent can use `list_zones` to propose new podcasts for ad placements. At the same time, a 'Budget Guardian' agent can use `get_audio_performance` to check if underperforming campaigns can be cut to free up funds. This isn't just a script; it's a negotiation powered by real data. AutoGen forces the agents to discuss the options and reach a consensus. The final decision is stronger because the data from the AdsWizz MCP server was used to challenge assumptions.

Setup guide

Set up AdsWizz 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 AdsWizz 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="AdsWizz_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the `mcp_server_tools` function from the `autogen-ext` package. Pass it your Vinkius server URL, and it returns a list of tools. You can then assign this tool list to your `AssistantAgent` during its setup.

Yes, that's exactly how AutoGen is meant to be used. You can have one agent specializing in performance data with `get_audio_performance` and another agent monitoring inventory with `list_zones`, both contributing to the same conversation.

An agent decides based on the flow of the conversation and its defined role. If you ask an agent team to 'review our Q3 performance,' one of the agents will determine that `get_audio_performance` is the right tool for the job and execute it.

The debate helps uncover blind spots. A single agent might just pull performance data, but in AutoGen, another agent can challenge the date range or ask for campaign details, leading to a much more thorough analysis.

The server only accesses the AdsWizz data needed to execute the tools you call: campaign configurations, performance metrics, and ad zone lists. Your connection is secured via a single Vinkius token, and every tool execution happens in a new, isolated sandbox that is immediately discarded.

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