How to Use the ARGUS Cloud MCP in AutoGen

Q: How do I register ARGUS Cloud tools in AutoGen?

You install autogen-extmcp and use StreamableHttpServerParams with your Vinkius endpoint. The framework handles the tool translation for your agents.

Build multi-agent AutoGen systems that debate commercial real estate decisions. Connect your ARGUS Cloud data to agents that challenge each other's valuations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ARGUS Cloud MCP to AutoGen

Create your Vinkius account to connect ARGUS Cloud 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 ARGUS Cloud with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate live asset valuations

The `get_portfolio` and `get_asset` tools give your AutoGen agents hard data to argue over. You assign one agent to act as a risk assessor and another as an acquisition manager, feeding them both the same live property metrics. They don't just accept the first number they see. The risk agent might spot an anomaly in the asset details and demand the acquisition agent pull historical context, driving a consensus-based decision process.

Interrupt chats with system alerts

Firing up the `list_notifications` tool lets a dedicated monitoring agent watch for system alerts. When a high-priority warning hits the ARGUS account, this agent interrupts the ongoing conversation to flag the issue. The rest of the agent group pauses their current task to evaluate the alert. You build systems where critical real estate warnings force immediate reassessment of portfolio strategies.

Verify auth via MCP Server

Running `get_account_check` through this ARGUS Cloud MCP Server verifies your connection before the agents start talking. The `McpToolAdapter` automatically translates the real estate schema into something your `AssistantAgent` natively understands. Before any debate begins, a setup agent checks the system health. If the auth fails, the system halts immediately instead of burning tokens on empty arguments.

Setup guide

Set up ARGUS Cloud 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 ARGUS Cloud 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="ARGUS Cloud_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You install `autogen-ext[mcp]` and use `StreamableHttpServerParams` with your Vinkius endpoint. The framework handles the tool translation for your agents.

Yes. You can equip different agents with specific tools from the MCP Server. One agent handles `list_assets` while another exclusively runs `get_asset` for deep dives.

AutoGen excels at complex, subjective tasks. Instead of a single linear output, you get a transcript of multiple AI personas challenging the portfolio composition based on the live API data.

It does. The integration supports both stdio and Streamable HTTP transports, keeping the connection open while the agents deliberate over the asset metrics.

Nobody outside your environment. The MCP Server processes your asset lists, portfolio IDs, and system notifications in memory. The Vinkius sandbox destroys the session the moment your script terminates.

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