How to Use the Amilia MCP in AutoGen

Q: How do I load Amilia tools into AutoGen?

Install the MCP extension and use mcpservertools with a StreamableHttpServerParams configuration. Pass the resulting list directly into your AssistantAgent constructor.

Deploy debating AutoGen agents to manage recreation schedules and family accounts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amilia MCP to AutoGen

Create your Vinkius account to connect Amilia 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 Amilia with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate for program scheduling

The `list_programs` and `list_activities` tools provide the raw facts for your agents to negotiate schedules. A scheduling agent pulls available fall sessions while a constraints agent argues about overlapping times. They iterate until they find a workable schedule. Instead of a single prompt guessing the best fit, the agents call `list_activity_occurrences` repeatedly, verifying exact dates before finalizing the proposed itinerary.

Resolve account conflicts via MCP Server

You trigger the `list_accounts` and `list_registrations` tools to feed your AutoGen dispute resolution system. One agent flags double-bookings in a family's profile, prompting a second agent to verify the exact participant details. This debate catches errors before they affect users. The system cross-references the output of `get_account_details` against active registrations, discussing the correct action before presenting a finalized summary to the human operator.

Audit attendance records autonomously

The `get_attendance` tool hands raw check-in data to your compliance agents. An auditor agent reviews the roster for missing participants, then instructs a communication agent to draft follow-up messages based on the findings. Setup requires the `autogen-ext[mcp]` package. You pass the server URL into `mcp_server_tools`, and the `McpToolAdapter` automatically converts the JSON schemas into a format your conversational agents understand.

Setup guide

Set up Amilia 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 Amilia 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="Amilia_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the MCP extension and use `mcp_server_tools` with a `StreamableHttpServerParams` configuration. Pass the resulting list directly into your `AssistantAgent` constructor.

They share the tool definitions, but each agent decides independently when to call them. You can give the `get_program_details` tool to a researcher agent while keeping it away from the summarizer.

The MCP server rejects the invalid parameters and returns an error string. The agent reads this error, discusses the mistake with its peers, and attempts the tool call again with corrected inputs.

Standard IO is fully supported. If you prefer not to use Streamable HTTP, you can pipe the tool execution directly through your terminal environment.

Every request runs in an ephemeral V8 Isolate. The sandbox processes the check-in rosters and immediately terminates, leaving zero cache or memory traces of the children's names behind.

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