How to Use the NCREIF Custom Query MCP in OpenAI Agents SDK

Q: How do I configure NCREIF Custom Query with the OpenAI Agents SDK?

Install the openai-agents package and initialize the MCP Server using MCPServerStreamableHttp with your Vinkius endpoint. Pass the server instance directly to the Agent constructor, and the agent will discover the tools automatically.

Q: How does NCREIF Custom Query handle high-volume historical NPI requests in the OpenAI Agents SDK?

The gethistoricalnpi tool in this MCP Server handles large-scale date ranges efficiently. To keep your OpenAI Agents SDK agent fast, set cacheToolsList=True in your server parameters to cache the tool definitions.

Q: What is the best way to extract predefined KPIs in this SDK?

Use the getpredefinedkpi tool inside your agent's system prompt to fetch standard real estate metrics. The agent calls this tool directly, returning clean JSON payloads that map to your internal data models.

Fetch institutional real estate index data directly into your OpenAI Agents SDK production flows with zero configuration overhead.

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 OpenAI Agents SDK

Create your Vinkius account to connect NCREIF Custom Query to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run custom SQL queries via the OpenAI Agents SDK

Your agent uses the `execute_query` tool to pull raw institutional real estate data directly from the NCREIF database. It bypasses manual CSV exports by letting the agent structure its own SQL-like calls to isolate specific submarkets, property types, or regions on the fly. Because the SDK tracks agent actions, you can set strict guardrails around these raw database queries. The agent gets the exact records it needs to calculate yields, while you maintain complete control over what SQL structures run against the index.

Track historical returns with built-in tracing

Pulling historical benchmarks requires precision, and the `get_historical_npi` tool on this MCP Server delivers exactly that to your agent. Your agent calls this tool to retrieve historical NPI returns across decades, feeding clean index numbers straight into your valuation models. The OpenAI dashboard logs every single one of these historical data fetches. You get full visibility into how your agent compares raw index returns against your portfolio's performance without guessing which tool call generated which chart.

Build multi-agent real estate analysis pipelines

You can set up one agent to pull macro trends with `get_predefined_kpi` and another to drill down into specific regional assets. This MCP Server lets these specialized agents hand off tasks to each other without losing the context of the real estate query. Instead of building complex routing code, you let the SDK handle the handoffs while the agents share access to the NCREIF tools. One agent verifies the high-level KPI, and the next agent immediately runs a deeper query to verify the underlying property data.

Setup guide

Set up NCREIF Custom Query MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all NCREIF Custom Query tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives NCREIF Custom Query tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NCREIF Custom Query tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="NCREIF Custom Query Agent",
            instructions="You have access to NCREIF Custom Query tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the `openai-agents` package and initialize the MCP Server using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass the server instance directly to the Agent constructor, and the agent will discover the tools automatically.

Yes, because you can set up guardrails directly in the SDK to inspect `execute_query` calls before they run. This prevents the agent from executing malformed SQL-like queries on the NCREIF database.

The `get_historical_npi` tool in this MCP Server handles large-scale date ranges efficiently. To keep your OpenAI Agents SDK agent fast, set `cacheToolsList=True` in your server parameters to cache the tool definitions.

Use the `get_predefined_kpi` tool inside your agent's system prompt to fetch standard real estate metrics. The agent calls this tool directly, returning clean JSON payloads that map to your internal data models.

Your SQL queries, historical NPI parameters, and KPI requests run inside an isolated Vinkius MCP sandbox. Your raw credentials never touch the LLM, and all data transit is encrypted end-to-end.

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