How to Use the Northbeam MCP in AutoGen

Q: Can I have one AutoGen agent check the work of another with Northbeam?

Absolutely. Have one agent call createdataexport, then have a second 'Auditor' agent use getexportstatus to verify it completes. This is a core pattern for AutoGen.

Q: What's the setup for using Northbeam tools with AutoGen?

Install autogen-extmcp and use the mcpservertools function with your server URL. This automatically provides the tools in a format you can pass directly to your AssistantAgent.

Q: How do my AutoGen agents decide which Northbeam attribution model to use?

They debate it. One agent can fetch options using listattributionmodels, another can argue for a specific one based on its goals, and they'll reach a consensus before acting.

Let your AutoGen agents debate Northbeam attribution strategies and converge on the best way to export data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Northbeam MCP to AutoGen

Create your Vinkius account to connect Northbeam 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 Northbeam with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Argue Over Metrics

This is where AutoGen shines. An 'Analyst' agent can call `list_metrics` and `list_breakdowns` to propose a detailed report. A 'Finance' agent can argue it's too granular and will take too long. The agents go back and forth, refining the parameters for the `create_data_export` call. They reach a consensus before any action is taken, so the final export request is one that satisfies multiple constraints.

Multi-Agent Export Verification

Use one agent to trigger a report with `create_data_export`. A second 'Auditor' agent's only job is to watch it, using `get_export_status` to monitor progress. Once the Auditor agent confirms the export is 'completed', it can notify a third 'Data' agent to fetch the results. This creates a clear separation of concerns, with agents collaborating to get the job done right. This MCP Server gives your team of agents the tools they need to work together.

Configure and Validate as a Team

Before running any reports, a 'Compliance' agent can use `get_account_info` and `list_attribution_models` to confirm the account is using an approved attribution model. If the model is wrong, it can flag it in the conversation, stopping other agents from proceeding. This prevents your team of agents from running reports based on bad assumptions. The agents use the toolset to keep each other honest.

Setup guide

Set up Northbeam 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 Northbeam 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="Northbeam_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You assign the tools to different agents. For instance, a 'Planner' agent uses `list_metrics` to propose an export, and a 'Worker' agent uses `create_data_export` to execute it after getting approval.

Absolutely. Have one agent call `create_data_export`, then have a second 'Auditor' agent use `get_export_status` to verify it completes. This is a core pattern for AutoGen.

Install `autogen-ext[mcp]` and use the `mcp_server_tools` function with your server URL. This automatically provides the tools in a format you can pass directly to your `AssistantAgent`.

They debate it. One agent can fetch options using `list_attribution_models`, another can argue for a specific one based on its goals, and they'll reach a consensus before acting.

It's secure. The entire multi-agent conversation and tool execution happens through your Vinkius endpoint. The server itself is ephemeral and only handles the specific Northbeam ad spend and revenue data your agents request during their session.

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