How to Use the Aspire MCP in AutoGen

Q: How does the Aspire integration work with an AutoGen group chat?

You can have multiple agents in a GroupChat. When one agent needs data, it calls an Aspire tool via the MCP Server. The result is posted back into the chat, where all the other agents can see it, react to it, and use it in their own reasoning.

Assemble a team of AutoGen agents to debate marketing strategy using live data from your Aspire account.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aspire MCP to AutoGen

Create your Vinkius account to connect Aspire 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 Aspire with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Simulate a Campaign Strategy Meeting

Give different Aspire tools to different agents and watch them work together. A 'Campaign Manager' agent can use `list_projects` and `get_project` to provide a high-level overview. A 'Talent Scout' agent can use `list_project_members` and `get_member` to analyze the creator roster for a specific campaign. They don't just dump data. The agents converse, challenge each other's findings, and work towards a consensus. You get a transcript of their 'meeting', which explains how they arrived at their strategic recommendations for your Aspire campaigns.

Debate Content Performance

Set up a group chat with specialized agents. One agent, the 'Analyst', uses `list_posts` and `get_post` to find the content with the highest engagement. Another agent, the 'Brand Guardian', can review the content's description for alignment with campaign goals. This creates a system of checks and balances. The Analyst might push to promote a viral post, but the Guardian might flag it as off-brand. Their debate helps you make a more considered decision than a single agent ever could. It’s decision support, not just data retrieval.

Multi-Agent Systems with this MCP Server

AutoGen excels at modeling complex collaboration, and this MCP Server provides the ground truth. The `mcp_server_tools` function makes it trivial to equip your agents with the ability to query your Aspire account. There's no custom integration code needed. The adapter handles converting the MCP tool schemas into a format AutoGen's `AssistantAgent` understands. You can focus on designing the agent roles and conversation flow, knowing the data they're debating is real and up-to-date.

Setup guide

Set up Aspire 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 Aspire 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="Aspire_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

When you define your agents, you can pass a specific list of tools to each one's constructor. For example, give the 'reporting_agent' the `list_projects` tool and the 'creator_agent' the `get_member` tool. This way, they have specialized roles in the conversation.

This setup is great for complex analysis that benefits from multiple viewpoints. Use it for post-campaign reviews, brainstorming for new campaigns based on past performance, or auditing creator rosters for brand fit. The agents' debate surfaces insights you might miss.

You can have multiple agents in a `GroupChat`. When one agent needs data, it calls an Aspire tool via the MCP Server. The result is posted back into the chat, where all the other agents can see it, react to it, and use it in their own reasoning.

No, AutoGen is for building collaborative autonomous systems. The 'chat' is the mechanism for agents to reason together and solve problems, like figuring out why a campaign is underperforming using data from Aspire. The final output is a solution, not just conversation.

Your agents access campaign data, creator info, and post metrics from Aspire. Each tool call is a discrete, stateless transaction through the Vinkius MCP endpoint. The data is only present for the life of the request and is never logged or stored on our platform.

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