How to Use the Urbanise MCP in AutoGen

Q: Can AutoGen handle Urbanise accounting ledgers?

Yes. You can have one agent list accounts using listaccountingledgers, and another challenge that list, ensuring every required ledger is accounted for before proceeding with reporting.

Q: Does AutoGen help manage Urbanise webhook configurations?

It can. You could deploy two agents—one listing listconfiguredwebhooks and another checking the system's health (checkapihealth)—to debate if the current webhooks are sufficient or if a new one is needed.

Q: What data types can AutoGen process from Urbanise?

It handles everything: property plans, resident lists via listpropertyoccupants, and supplier details. The agents use these disparate data points to argue toward a single, actionable conclusion.

Debating Optimal Property Operations Decisions with AutoGen and Urbanise MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Urbanise MCP to AutoGen

Create your Vinkius account to connect Urbanise 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 Urbanise with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus on New Maintenance Jobs

Use multiple agents to debate a maintenance decision. One agent might check `list_property_budgets` for funding, while another lists assets using `list_facility_assets`. A third agent then recommends the job title and description needed for `create_maintenance_job`. The system reaches consensus on *whether* the job should proceed based on competing financial and inventory checks.

Reviewing Complex Financial Decisions

Have agents debate billing issues. One agent pulls raw data with `list_financial_data`, while a second agent cross-references that against client details using `get_client_profile`. They argue over discrepancies until they settle on the necessary adjustments. It's ideal for complex financial reconciliation where multiple perspectives are needed.

Auditing Property Plans and Occupants

Set up a debate between two agents: one listing `list_property_plans` and another listing `list_property_occupants`. They argue about which plan segment is currently under-occupied or over-budget. The outcome isn't just a list; it's the reasoned conclusion on where management focus should shift.

Setup guide

Set up Urbanise 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 Urbanise 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="Urbanise_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

It moves beyond simple automation. Instead of running a script, agents debate options—for instance, debating the best timing to run `create_maintenance_job` based on asset status and current budgets.

Yes. You can have one agent list accounts using `list_accounting_ledgers`, and another challenge that list, ensuring every required ledger is accounted for before proceeding with reporting.

It can. You could deploy two agents—one listing `list_configured_webhooks` and another checking the system's health (`check_api_health`)—to debate if the current webhooks are sufficient or if a new one is needed.

It handles everything: property plans, resident lists via `list_property_occupants`, and supplier details. The agents use these disparate data points to argue toward a single, actionable conclusion.

This MCP Server touches resident names and owner information via `list_property_occupants`. When designing agent debates, ensure the discussion protocols mask or redact sensitive personal identifiers.

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