How to Use the NCREIF Custom Query MCP in Pydantic AI

Q: How do I set up NCREIF Custom Query with Pydantic AI?

Install the framework with MCP support and initialize MCPToolset with your Vinkius HTTP endpoint. Pass the toolset directly to your agent to start executing type-safe real estate queries.

Q: How does Pydantic AI prevent errors when running NCREIF Custom Query operations?

The framework validates the JSON payload returned by executequery against your Pydantic models. If the database returns unexpected schema structures, the agent catches the validation error immediately.

Run type-safe NCREIF Custom Query operations with Pydantic AI to guarantee valid real estate data in your production pipelines.

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 Pydantic AI

Create your Vinkius account to connect NCREIF Custom Query 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 Custom Query with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe raw SQL queries for Pydantic AI

When your agent uses the `execute_query` tool to pull index data, you cannot afford silent database errors. Pydantic AI validates the incoming NCREIF SQL response schema against your Python models at runtime, failing immediately if the database returns unexpected formats. This strict validation prevents your agent from passing malformed real estate records to downstream financial models. You write clean, typed code knowing that the custom query outputs match your exact database expectations.

Validate historical NPI returns at runtime

Historical benchmarks are the foundation of your valuation models, so the data must be flawless. Your agent calls `get_historical_npi` to pull historical index returns, and the framework ensures every row matches your defined data structures. If the NCREIF API updates its schema or returns empty values, your agent catches it before it can corrupt your calculations. This makes the MCP Server reliable enough for production financial systems where accuracy is non-negotiable.

Fetch structured real estate KPIs without hallucinations

Real estate metrics can be complex, but the `get_predefined_kpi` tool returns clean, structured data points. Your Pydantic AI agent reads these KPIs directly into validated Python objects, eliminating the risk of the model hallucinating key performance numbers. This tool provides a direct path to standard index benchmarks. Because the framework is model-agnostic, you can switch from Anthropic to OpenAI without changing how your agent validates these NCREIF metrics using this MCP Server.

Setup guide

Set up NCREIF Custom Query 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-custom-query-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent NCREIF Custom Query 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 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 Pydantic AI

Install the framework with MCP support and initialize `MCPToolset` with your Vinkius HTTP endpoint. Pass the toolset directly to your agent to start executing type-safe real estate queries.

The framework validates the JSON payload returned by `execute_query` against your Pydantic models. If the database returns unexpected schema structures, the agent catches the validation error immediately.

Yes, because the framework is model-agnostic. You can connect your local model to the NCREIF Custom Query MCP Server and still get full schema validation on every historical index query.

Use the Streamable HTTP transport provided by Vinkius for this MCP Server. This ensures a stable, secure connection for your agent to fetch historical returns via `get_historical_npi`.

All index queries, KPI requests, and historical parameters are processed in zero-trust, ephemeral V8 sandboxes. Your database credentials and raw search parameters are never cached or exposed to third parties.

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