How to Use the Alai MCP in AutoGen

Q: How do my AutoGen agents access the Alai tools?

You use the mcpservertools function from the AutoGen extension library. It connects to the Alai MCP Server and provides a list of tools like createcampaign that you can directly assign to an AssistantAgent.

Q: What's a simple multi-agent setup for Alai with AutoGen?

A simple pair would be a UserProxyAgent and an AssistantAgent. The user asks for a new headshot. The AssistantAgent, equipped with Alai tools, asks for a selfie, calls createasset and generatecontent, then returns the final image URL.

Assemble a team of AutoGen agents to debate, plan, and execute marketing campaigns using Alai's headshot tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Alai MCP to AutoGen

Create your Vinkius account to connect Alai 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 Alai with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Campaigns with Agent Debates

With the Alai MCP Server, you can assign different roles to your AutoGen agents for a full marketing workflow. One agent acts as a "Creative Director," proposing a new campaign by calling `create_campaign`. A second "Asset Manager" agent can then challenge the plan, first checking for existing photos with `list_assets` to avoid duplicate work. The agents converse and agree on a plan before any images are actually generated with `generate_content`.

A Multi-Agent System for Alai

Go beyond simple tool execution. You can build a system where one agent is responsible for uploading source photos with `create_asset`, while another agent's only job is to monitor progress by calling `get_generation`. This separation of concerns is AutoGen's strength. You can even have a "QA Agent" that retrieves the final asset with `get_asset` and asks you for approval, creating a human-in-the-loop workflow. This MCP server gives your agent team the functions they need to collaborate.

Plan and Execute with Consensus

AutoGen lets your agents negotiate the best way to use the Alai tools. For instance, a "Planner" agent could fetch available styles using `list_templates` and propose three options for a new campaign. A "Critic" agent could then argue against one of them based on the campaign's brief. They reach a consensus before the "Executor" agent finally calls `generate_content` with the agreed-upon template. This reduces errors and ensures the final output matches the original goal.

Setup guide

Set up Alai 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 Alai 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="Alai_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You use the `mcp_server_tools` function from the AutoGen extension library. It connects to the Alai MCP Server and provides a list of tools like `create_campaign` that you can directly assign to an `AssistantAgent`.

Yes, that's a perfect use case for AutoGen. You'd have the first agent call `create_campaign` and share the resulting campaign ID with a second agent. The second agent then uses that ID to call `create_asset` and `generate_content`.

A simple pair would be a `UserProxyAgent` and an `AssistantAgent`. The user asks for a new headshot. The AssistantAgent, equipped with Alai tools, asks for a selfie, calls `create_asset` and `generate_content`, then returns the final image URL.

When an Alai tool call fails, the error is passed back to the agent that made the call. You can design your agent conversation so that if one agent gets an error from `generate_content`, it reports the failure to another agent or the user, who can then decide how to proceed.

Your source photos are only handled by the Alai server to generate the headshot. The Vinkius platform isolates every MCP Server, so the image data for your `create_asset` call is processed securely and is not visible to other servers or tenants.

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