How to Use the NCREIF MCP in LangChain

Q: Can a LangChain agent use NCREIF data to decide which fund to analyze?

Yes. You can build a chain where the agent first calls listfunds, then uses criteria you provide to select a fund and pass its ID to getfundperformance. The agent makes the connection automatically.

Q: What's the best way to list all available NCREIF indices in a LangChain app?

Just have your agent call the listindices tool. It returns a clean list of available indices like NPI and ODCE, which you can then use as input for the getindexdata tool in the next step of your chain.

Build real estate data chains with LangChain. Query NCREIF performance, funds, and properties in sequence.

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 LangChain

Create your Vinkius account to connect NCREIF to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Multi-Step CRE Analysis

Start by listing available NCREIF performance indices with `list_indices`. Feed that output directly into `get_index_data` to pull historical trends for the NPI or ODCE. It's all one chain. Your agent decides the next step. If the index data shows a dip in office performance, it can automatically trigger `get_property_type_data` for 'Office' to dig deeper. LangSmith traces every step, showing you exactly what data the agent used to make its decision.

Compare Funds and Properties

This MCP Server lets your agent find specific real estate funds using `list_funds`. From there, a second step in your chain can call `get_fund_performance` to see how it's done over time. No manual lookups. Build more complex logic. For example, find the top-performing fund, then use `list_properties` to see what kind of assets it holds, and finally run `get_property_returns` on a specific property ID. Your chain executes the entire research workflow.

Regional Deep Dives with LangChain

Go beyond national trends. Use `get_region_data` to have your LangChain agent compare commercial real estate performance across different parts of the country. Is the West outperforming the South? The data will tell you. Combine this with other tools in a chain. For instance, identify a hot region, then use `list_market_data` to get more granular details for that specific market. This is how you build an agent that doesn't just answer questions, but performs genuine discovery.

Setup guide

Set up NCREIF MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes NCREIF tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "ncreif-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent NCREIF transactions"
    })
    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 LangChain

You create an agent and give it the NCREIF tools. Then, ask it to compare office and industrial returns. The agent will likely call `get_property_type_data` for each type and present the results.

Yes. You can build a chain where the agent first calls `list_funds`, then uses criteria you provide to select a fund and pass its ID to `get_fund_performance`. The agent makes the connection automatically.

Absolutely. LangSmith will show you every call your agent makes to the NCREIF MCP Server, including the inputs and the structured data that comes back. This gives you full visibility into the agent's reasoning.

Just have your agent call the `list_indices` tool. It returns a clean list of available indices like NPI and ODCE, which you can then use as input for the `get_index_data` tool in the next step of your chain.

Vinkius handles the connection. Your single endpoint token authenticates you to the MCP server, which then securely accesses NCREIF data. No fund performance data, property returns, or index values are stored long-term on the server.

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