How to Use the NCREIF MCP in Google ADK

Q: How do I configure the NCREIF MCP Server for Google ADK?

Install google-adk via pip. Create a McpToolset with your Vinkius HTTP endpoint and assign it to the tools array in your LlmAgent.

Q: Can I restrict which NCREIF tools Google ADK uses?

Yes. You can apply a toolnames filter when setting up the toolset. This lets you expose getpropertyreturns while hiding listfunds from specific agents.

Q: Are my regional market queries logged by the server?

Never. We process every getregiondata request inside a secure, single-use V8 Isolate. The instance is destroyed the millisecond your data is returned, ensuring your investment focus remains entirely private.

Bring NCREIF commercial real estate metrics into your Google ADK pipelines.

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 Google ADK

Create your Vinkius account to connect NCREIF to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query NCREIF inside Google ADK

Enterprise agents need hard numbers. This MCP Server connects your Google ADK setup straight to NCREIF's property and fund databases. Your Gemini models can now cross-reference institutional real estate data with your internal BigQuery tables. The integration is straightforward. You wrap the server URL in a `McpToolset` and hand it to your `LlmAgent`. From there, the agent can call `list_indices` or `get_index_data` whenever a user asks about market performance.

Analyze Deep Property Histories

Gemini's massive context window is useless if you feed it garbage. Give it actual market history by having it call `list_market_data` and `list_data_series`. It can pull decades of institutional real estate returns into a single prompt. Once the agent has the broad trends, it can zero in. It uses `get_property_type_data` to isolate retail versus industrial performance. You get analysis backed by real NCREIF metrics, not internet summaries.

Evaluate Fund and Region Spreads

Tracking how specific funds perform against regional benchmarks requires heavy lifting. Now your agent does it for you. It hits `list_funds` to find the targets, then runs `get_fund_performance` to pull the numbers. It compares those fund returns against local baselines using `get_region_data` and `get_property_returns`. Because it is running through Google ADK, you can easily pipe the resulting analysis directly into Vertex AI workflows.

Setup guide

Set up NCREIF MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with NCREIF tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="NCREIF_agent",
    model="gemini-2.0-flash",
    instruction="You have access to NCREIF tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install `google-adk` via pip. Create a `McpToolset` with your Vinkius HTTP endpoint and assign it to the `tools` array in your `LlmAgent`.

Yes. You can apply a `tool_names` filter when setting up the toolset. This lets you expose `get_property_returns` while hiding `list_funds` from specific agents.

It supports both Stdio and HTTP transports natively. For Vinkius-managed servers, you will use the Streamable HTTP parameters.

Gemini reads the tool schemas and writes the exact arguments required. If you ask for office returns, it knows to call `get_property_type_data` with the correct sector parameters.

Never. We process every `get_region_data` request inside a secure, single-use V8 Isolate. The instance is destroyed the millisecond your data is returned, ensuring your investment focus remains entirely private.

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