How to Use the NCREIF MCP in AutoGen

Q: Can I set up a 'research team' of AutoGen agents with the NCREIF connector?

Absolutely. One agent can use listdataseries to see what's available, another can fetch the data with getindexdata, and a third can summarize the findings. They work together in a conversational workflow.

Q: How do I give my AutoGen assistant access to the NCREIF tools?

Use the mcpservertools function from the autogen-extmcp package. You pass it your server URL, and it returns a list of tool functions that you can register directly with your AssistantAgent.

Let your AutoGen agents debate real estate strategy using live NCREIF data. Reach consensus on market moves.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NCREIF MCP to AutoGen

Create your Vinkius account to connect NCREIF 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 NCREIF with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Model an Investment Committee

Create a team of agents. One agent, the 'Analyst,' uses `get_index_data` and `get_property_type_data` to present market trends. Another agent, the 'Portfolio Manager,' uses `list_properties` and `get_property_returns` to check your specific holdings against those trends. The agents don't just execute tasks; they talk to each other. The Analyst might propose selling office assets based on national data, but the Portfolio Manager can push back with performance data on your specific buildings. This surfaces a more nuanced conclusion.

Debate Regional Opportunities

This MCP Server provides the raw material for a strategic debate. Task a 'Growth' agent with finding high-performing areas using `get_region_data`. At the same time, have a 'Risk' agent check the volatility of those same regions. The agents will present their findings and challenge each other's assumptions. The Growth agent might point to high returns, but the Risk agent can counter by showing that the income component is unstable. The final output is a consensus, not just a data dump.

An MCP Server for Agent Deliberation

AutoGen's strength is conversation. Give your agents access to tools like `list_funds` and `get_fund_performance`. One agent can propose an investment based on a fund's recent returns. A second 'Due Diligence' agent can then be tasked to critique that choice, maybe by using `get_index_data` to show the fund is just tracking a hot index and not generating real alpha. This back-and-forth leads to better automated decisions.

Setup guide

Set up NCREIF 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 NCREIF 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="NCREIF_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You assign the NCREIF tools to different agents with different goals. For example, an 'optimist' agent uses `get_property_type_data` to find growth, while a 'pessimist' agent uses the same tool to look for downturns, sparking a debate.

Absolutely. One agent can use `list_data_series` to see what's available, another can fetch the data with `get_index_data`, and a third can summarize the findings. They work together in a conversational workflow.

Use the `mcp_server_tools` function from the `autogen-ext[mcp]` package. You pass it your server URL, and it returns a list of tool functions that you can register directly with your AssistantAgent.

A strong pattern is a UserProxy agent that talks to an Analyst agent. The Analyst has access to all NCREIF tools and can call `get_fund_performance` or `get_region_data` as needed to answer the user's questions, explaining its steps as it goes.

The MCP server that AutoGen connects to is stateless. It fetches NCREIF fund or property data for your agents' conversation and then discards it. Vinkius ensures the connection is secure and the compute environment is isolated.

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