How to Use the NCREIF MCP in Windsurf

Q: How do I install the NCREIF MCP Server in Windsurf?

Open your mcpconfig.json file or use the Settings menu to navigate to the Cascade MCP Servers UI. Add the NCREIF endpoint under mcpServers and click refresh. Cascade will automatically discover the ten real estate tools.

Q: Can Windsurf pull historical NCREIF index data?

Yes, Cascade uses the getindexdata tool to fetch historical performance metrics. You just tell it the timeframe and index you want. It handles the API calls and formats the output.

Q: What property types does NCREIF cover in Windsurf?

The getpropertytypedata tool accesses returns for office, retail, industrial, and multifamily assets. Cascade can pull the exact sector you specify and compare it against regional benchmarks.

Q: Will this MCP Server work for fund-level analysis?

It handles fund analysis perfectly. You run listfunds to find the target, then execute getfundperformance to pull the quarterly return history.

Pull institutional commercial real estate data straight into Windsurf with this MCP Server to model returns without leaving your editor.

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 Windsurf

Create your Vinkius account to connect NCREIF to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Institutional Capital with Windsurf

The `get_index_data` and `list_indices` tools let Cascade pull historical NPI and ODCE metrics directly into your workspace. You ask for a 10-year lookback on core funds, and Windsurf chains these requests to build the dataset. It doesn't stop at top-level indices. Cascade runs `list_funds` to find specific vehicles, then hits `get_fund_performance` to map out quarterly returns. You get the raw numbers formatted exactly how you need them for your financial models.

Drill Down into Submarkets

The `get_region_data` and `get_property_type_data` tools expose the geographic and sector spreads driving those macro returns. Cascade grabs the regional splits to show exactly where industrial is outperforming office. If you need granular comps, it triggers `list_properties` followed by `get_property_returns`. Windsurf assembles a complete breakdown of income versus appreciation returns for specific asset classes in seconds.

Automate Real Estate Data Pipelines

Using `list_market_data` and `list_data_series`, your AI client maps out the entire available NCREIF data universe. You don't have to guess which metrics are available for your analysis. Cascade reads the available series, selects the relevant commercial real estate datasets, and writes the Python scripts to parse them. This MCP Server turns a raw data feed into actionable code instantly.

Setup guide

Set up NCREIF MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the NCREIF MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my NCREIF payment history." If connected, Cascade will call the NCREIF tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "ncreif-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Windsurf

Open your mcp_config.json file or use the Settings menu to navigate to the Cascade MCP Servers UI. Add the NCREIF endpoint under mcpServers and click refresh. Cascade will automatically discover the ten real estate tools.

Yes, Cascade uses the get_index_data tool to fetch historical performance metrics. You just tell it the timeframe and index you want. It handles the API calls and formats the output.

The get_property_type_data tool accesses returns for office, retail, industrial, and multifamily assets. Cascade can pull the exact sector you specify and compare it against regional benchmarks.

It handles fund analysis perfectly. You run list_funds to find the target, then execute get_fund_performance to pull the quarterly return history.

Vinkius isolates your NCREIF API interactions inside an ephemeral V8 sandbox. When you query institutional property returns or fund metrics, the transport layer is strictly zero-trust. Your private queries vanish the second the connection drops.

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