How to Use the NCREIF MCP in LlamaIndex

Q: How do I get a list of available properties from NCREIF in LlamaIndex?

You give your FunctionAgent the McpToolSpec. Then, just ask it to 'list the indexed properties.' It will know to call the listproperties tool and return the results.

Ground your LlamaIndex RAG apps in live NCREIF data. Query property returns, indices, and fund performance.

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 LlamaIndex

Create your Vinkius account to connect NCREIF to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Real Estate Knowledge Base

Connect the NCREIF tools to your LlamaIndex agent. When you ask for market data using `get_region_data` or `get_property_type_data`, the agent doesn't just give you the answer. It indexes the results. The next time you ask a related question, the agent can pull from this indexed knowledge. This means your app gets smarter over time, grounding its answers in historical NCREIF data it's already seen, reducing redundant API calls.

Query Your API History

This MCP Server lets you pull specific fund metrics with `get_fund_performance` or property details with `get_property_returns`. With LlamaIndex, that data becomes a searchable asset. You can ask follow-up questions in plain English like, 'What were the returns for that property we checked last week?' The agent finds the answer in its vector index of past tool calls, giving you answers grounded in actual, retrieved data.

Live Data for LlamaIndex Agents

Your agent can use `list_indices` and `list_funds` to discover what data is even available. This keeps your RAG application from becoming stale. The agent can refresh its own context with the latest available data series from the MCP server. This isn't just about documents; it's about structured, live information. When you combine indexed PDFs with live API results from `get_index_data`, your agent can synthesize a report that's both deeply contextual and completely up-to-date.

Setup guide

Set up NCREIF MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all NCREIF MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to NCREIF tools.",
)
response = await agent.run("List recent NCREIF data")

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 LlamaIndex

LlamaIndex excels at indexing the output of the NCREIF tools. When your agent calls `get_property_returns`, that data can be stored in a vector database for future semantic queries, building a long-term memory for your application.

Yes, that's a primary use case. The agent can fetch data with `get_fund_performance` and `list_funds`, index it, and then answer natural language questions about fund strategies and historical returns.

You give your FunctionAgent the `McpToolSpec`. Then, just ask it to 'list the indexed properties.' It will know to call the `list_properties` tool and return the results.

The indexing happens within your LlamaIndex application. The MCP Server itself is ephemeral; it processes requests and doesn't store the NCREIF property or fund data it retrieves for you. You control where your index lives.

Your queries for NCREIF index data or property returns are processed by an ephemeral, sandboxed server instance on Vinkius. The server doesn't log or store the specific financial data returned by the API. Your connection is secured by a single token.

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