How to Use the NCREIF MCP in Pydantic AI

Q: How do I add the NCREIF MCP Server to Pydantic AI?

Install the slim package with MCP extras. Initialize an MCPToolset with your Vinkius HTTP URL and pass it to your Agent's toolsets parameter.

Q: Does Pydantic AI validate the NCREIF server responses?

It does. Every payload from tools like getpropertyreturns is checked against your defined models. If the schema breaks, the agent throws a validation error immediately.

Q: Is the old MCPServerHTTP method still used for the NCREIF MCP Server in Pydantic AI?

No. That approach is deprecated. You must use the unified MCPToolset class to connect to external servers over Streamable HTTP or SSE.

Q: Who can see my property return analysis on this MCP Server?

Nobody. We route your getpropertyreturns requests through ephemeral sandboxes. The execution environment is wiped clean right after the API responds, guaranteeing your asset-level research stays strictly confidential.

Type-safe access to NCREIF institutional real estate data for Pydantic AI agents.

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 Pydantic AI

Create your Vinkius account to connect NCREIF to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict NCREIF Validation in Pydantic AI

You cannot afford silent errors when dealing with commercial real estate returns. This MCP Server feeds NCREIF data directly into your Pydantic AI agents. Every single response is validated at runtime against strict schemas. If an API change causes `get_fund_performance` to return a string instead of a float, your agent fails loudly. No hallucinated cap rates. No corrupted database entries. You get exactly the data structure you expect.

Map Indices and Market Data

Building autonomous research agents requires reliable market baselines. Your AI client can pull the exact NPI or ODCE figures it needs by calling `list_indices` and `get_index_data`. Because Pydantic AI is model-agnostic, you can swap between Anthropic and local models without changing your tool logic. The agent pulls the historical context using `list_data_series` and `list_market_data`, and the framework ensures the inputs are perfectly typed.

Drill Down to Property Types and Regions

Broad market data only gets you so far. When you need to compare industrial against office, the agent executes `get_property_type_data`. It gets the sector splits formatted exactly as your application requires. Then it goes deeper. The agent can fire off `get_region_data` to check geographic performance, or use `list_properties` and `get_property_returns` for specific asset classes. You define the expected Pydantic models, and the framework guarantees the output matches.

Setup guide

Set up NCREIF MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "ncreif-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to NCREIF tools.",
)

result = await agent.run("List recent NCREIF transactions")
print(result.output)

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 Pydantic AI

Install the slim package with MCP extras. Initialize an `MCPToolset` with your Vinkius HTTP URL and pass it to your Agent's `toolsets` parameter.

It does. Every payload from tools like `get_property_returns` is checked against your defined models. If the schema breaks, the agent throws a validation error immediately.

No. That approach is deprecated. You must use the unified `MCPToolset` class to connect to external servers over Streamable HTTP or SSE.

Yes. Pydantic AI abstracts the model layer. You can use an open-source model to call `list_funds` just as easily as you would use GPT-4.

Nobody. We route your `get_property_returns` requests through ephemeral sandboxes. The execution environment is wiped clean right after the API responds, guaranteeing your asset-level research stays strictly confidential.

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