How to Use the NCREIF Custom Query MCP in Google ADK

Q: How do I connect NCREIF Custom Query to my Google ADK agent?

Initialize McpToolset using your Vinkius HTTP endpoint for this MCP Server and pass it to your LlmAgent. The tools are immediately available to your Gemini model for querying real estate indices.

Q: Can I limit the NCREIF Custom Query tools my Google ADK agent can access?

Yes, you can use the toolnames filter in the ADK server parameters to restrict access. For example, you can expose only getpredefinedkpi if you want to block raw SQL execution.

Q: How does Gemini use gethistoricalnpi to build real estate models?

The model calls gethistoricalnpi to fetch raw index returns, then uses its reasoning capabilities to compare those benchmarks against your internal property performance.

Connect Gemini's 1M+ token context to institutional NCREIF index data using the Google ADK for enterprise real estate analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NCREIF Custom Query MCP to Google ADK

Create your Vinkius account to connect NCREIF Custom Query 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 Custom Query with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject NCREIF data into Gemini's long context

Gemini models need lots of data to find patterns, and this MCP Server feeds them raw index numbers. Your agent uses `get_historical_npi` to pull decades of return data, dumping the entire historical payload directly into Gemini's massive context window. The Google ADK makes this process simple by letting your agent query the database and analyze the results in a single run. The agent reads the historical trends and compares them against your private market datasets without hitting token limits.

Run custom SQL queries via Google ADK

Enterprise real estate teams keep their proprietary assets in BigQuery, but they need NCREIF benchmarks to value them. Your Google ADK agent uses the `execute_query` tool to pull live index benchmarks alongside your internal tables. You can restrict which tools the agent sees by using the tool names filter in the ADK setup. This ensures your agent only executes the specific SQL queries via the MCP Server needed to align your internal portfolio data with external benchmarks.

Fetch predefined performance KPIs on Google Cloud

Pulling standard real estate performance metrics shouldn't require complex database joins. Your agent calls the `get_predefined_kpi` tool to fetch clean, structured performance indicators directly into your cloud workflow. This tool provides the exact numbers your agent needs to build automated reporting pipelines. Because the ADK integrates with Google Cloud, you can trigger these KPI fetches on a schedule and pipe the results to your dashboards.

Setup guide

Set up NCREIF Custom Query 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 Custom Query 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 Custom Query_agent",
    model="gemini-2.0-flash",
    instruction="You have access to NCREIF Custom Query 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 Custom Query 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 Custom Query MCP in Google ADK

Initialize `McpToolset` using your Vinkius HTTP endpoint for this MCP Server and pass it to your `LlmAgent`. The tools are immediately available to your Gemini model for querying real estate indices.

Yes, you can use the `tool_names` filter in the ADK server parameters to restrict access. For example, you can expose only `get_predefined_kpi` if you want to block raw SQL execution.

It does. While Stdio works great for local testing, you will want to use the HTTP transport with your Vinkius token when deploying your agent to Google Cloud for this MCP Server.

The model calls `get_historical_npi` to fetch raw index returns, then uses its reasoning capabilities to compare those benchmarks against your internal property performance.

Your custom SQL queries and historical requests pass through secure, ephemeral Vinkius MCP isolates. No real estate data is stored on external servers, keeping your proprietary investment strategies completely 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