Ed Neuhaus 
Cursor just crossed billion in annual revenue. That makes it the fastest-growing code editor in history, and roughly 70% of the Fortune 1000 has engineering teams running it right now. So when we built the Austin MLS MCP connector, Cursor was at the top of the compatibility list. One JSON config block and you can search Austin real estate listings from NeuhausRE.com right inside your coding environment. Listings, comps, market stats, the same property data displayed on our website, just delivered programmatically.
If you are a developer building property tools, an investor who writes scripts to analyze deals, or just someone who lives in Cursor and wants Austin real estate data without switching tabs, this is for you. And yeah, the setup takes about 90 seconds.
What Cursor Actually Is (And Why It Matters Here)
For anyone in real estate reading this who hasnt used it, Cursor is an AI-native code editor built on top of VS Code. Think of VS Code but with AI baked into every part of the experience. You can chat with your codebase, generate code from natural language, and (this is the part that matters for us) connect to external data sources through something called MCP.
MCP stands for Model Context Protocol. I wrote a full explainer on what MCP means for real estate if you want the deep dive. But the short version is this: MCP is a bridge that lets your AI tools talk to live data sources. Instead of copy-pasting data from a website into your editor, the editor just pulls it directly.
Peter Thiel’s whole argument in Zero to One is that the most valuable businesses build something nobody else has. Useful information connected to the tools people actually use. That is exactly what this is right. Austin property data from NeuhausRE.com flowing into the environment where developers and investors actually work.
Why You Would Want Austin Property Data Inside Cursor
Ok lets be practical about this. Who actually benefits from having Austin property data inside Cursor?
Real estate developers (the software kind). If you are building property search tools, investment calculators, or anything that touches listing data, you need a data source. And you probably need to test queries constantly while you code. Having property data one prompt away inside your editor means you can write a function, test it against real listings, and iterate without ever leaving Cursor. No separate API console. No Postman tabs. Just ask.
Investors who code. I know a surprising number of RE investors who write Python scripts to screen deals. Pull comps for a zip code, calculate cash-on-cash return, filter by days on market. If that is you, connecting to NeuhausRE.com through Cursor turns your editor into a deal analysis machine. You can ask for every listing under 00,000 in 78738 with 4+ bedrooms and get real results right there in your workspace.
Agents building internal tools. This one is close to home for me. At Neuhaus Realty Group I have been building my own tools for years because the off-the-shelf stuff never quite does what I need (a story most agents know well right). Cursor with MLS access means you can prototype and test tools against live data as you build them.
And honestly even if you are just curious about Austin real estate data and you happen to live in Cursor all day, this is the lowest-friction way to explore it.
Step-by-Step: Connecting Cursor to Austin Real Estate Data
Here is the actual setup. I’m going to walk through this like I would if you were sitting next to me.
Step 1: Open Your MCP Config File
Cursor stores its MCP server configurations in a file called mcp.json. You have two options for where to put it:
- Global (recommended):
~/.cursor/mcp.jsonin your home directory. This makes the Austin MLS available in every project you open. - Project-level:
.cursor/mcp.jsonin your project root. Use this if you only want MLS access in a specific codebase.
If the file doesnt exist yet, create it. No big deal. If it already exists with other servers configured (and if you are a Cursor power user you probably have a few in there already), you will just add to the existing mcpServers object.
Step 2: Add the NeuhausRE MCP Server
Add this config block to your mcp.json file:
{
"mcpServers": {
"austin-mls": {
"url": "https://mls.neuhausre.com/mcp"
}
}
}That is it. Seriously. The url field points to the NeuhausRE.com property data endpoint, and Cursor handles the rest. No API keys to manage, no npm packages to install, no command-line arguments to configure.
If you already have other MCP servers configured, just add the "austin-mls" entry inside your existing mcpServers block. No need to replace anything.
Step 3: Restart Cursor and Authorize
After saving the config file, restart Cursor (or reload the window). Then go to Settings > Tools & MCP to verify the server loaded. You should see “austin-mls” with a green status indicator.
The first time Cursor connects to the server, it will prompt you to authorize through OAuth. This is standard OAuth 2.1 with PKCE, and Cursor handles the whole handshake automatically through its built-in redirect callback. You will see a signup form asking for your name, email, and phone number. Fill it out, authorize, done.
No big deal right. You don’t need to configure any OAuth credentials in your config file. The server and Cursor negotiate that for you.
Step 4: Start Asking Questions
Once authorized, you have four tools available in Cursor’s AI chat:
- search_listings – Find active listings by location, price, beds, baths, features
- get_listing – Pull full details on a specific property
- get_comps – Get closed-sale comparables by address, radius, and date range
- get_market_stats – Median prices, inventory levels, days on market by location
Open Cursor’s chat (Cmd+L or Ctrl+L) and start asking in natural language. The AI figures out which tool to call. You don’t need to know the tool names or pass structured arguments. Just ask like you would ask a person.
Example Prompts to Try Once Connected
So you are connected. Now what? Here are some real prompts you can throw at Cursor to see what comes back. These are the kinds of questions I ask myself when I’m evaluating a market or helping a client run numbers.
Searching for listings:
- “Show me all active listings in Bee Cave under 00,000 with at least 3 bedrooms”
- “Find homes in Lakeway with a pool that have been on the market more than 30 days”
- “What is available in 78738 between 00K and 00K?”
Pulling comps:
- “Get me comparable sales within half a mile of 123 Main St, Bee Cave TX from the last 6 months”
- “Show closed sales in Lakeway over M in the last 90 days”
Market stats:
- “What is the median home price in Bee Cave right now?”
- “Show me inventory levels and days on market for Austin zip code 78746”
- “Compare median prices in Dripping Springs vs Bee Cave”
But the beauty of having this inside Cursor specifically is that you can take those results and immediately use them in your code. Write a function that calls search_listings, pipe the results into a pandas DataFrame, calculate your own metrics. Or just use it as a quick reference while you are building something else entirely. Either way the data is right there in your workspace. No context switching.
Free Access and Active Buyer Retainers
The NeuhausRE MCP connector is free to use. You get 10 results per search, 10 queries per hour, and 100 queries per month. That is plenty for exploring, building tools, and casual property research.
If you are actively searching for a home in Austin, we also offer an Active Buyer retainer at 00/month. That bumps your throughput to 50 results per search, 200 queries per hour, and 10,000 per month, plus unlocks comps and market stats. Think of it as a buyer representation retainer, not a data subscription. And the whole amount gets credited back to you at closing if you purchase through us. So if you end up buying a home in Austin, you effectively paid nothing.
The data itself is free either way. The retainer is for buyers who want priority service and higher volume.
Beyond Cursor: Other AI Clients That Work
Cursor is one of several AI platforms that can connect to this same MCP server. If you also use Claude Desktop, we have a dedicated setup guide for connecting Claude to the Austin MLS. The full list of supported clients (ChatGPT, Perplexity, Gemini CLI, Windsurf, Cline, and more) lives on the main connector page.
The MCP protocol is the same across all of them, once you understand how it works in one client the concept transfers everywhere. I wrote a beginner’s guide to AI for real estate if you want the broader context on how all this fits together.
Why I Built This
I get asked about this so I will just say it plainly. Most real estate websites make you click through page after page to find what you need. Search, filter, click, back, search again. It works, but it is slow if you are trying to do serious analysis.
I built this connector because the same property data we display on NeuhausRE.com should be accessible in the tools people actually work in. Not just through a traditional search page (although we have that too). Not a chatbot that asks three questions and then demands your phone number before it tells you anything useful (I wrote a whole article about why that approach is broken). The same listings, the same comps, the same market data you would find browsing our site, just delivered through your AI tools instead of a web browser.
If you are an investor running comps in a Python script, you should be able to pull from the same property database that powers our website. If you are a developer building the next great property search tool, you shouldnt have to scrape aggregator sites and hope the data is still accurate by the time you ship. That is the whole point of putting this behind MCP.
And honestly it is good for my business too. People who use this data seriously tend to be serious buyers. Not tire kickers. The kind of people who pull comps and run numbers before they ever call an agent? Those are my favorite clients. We tend to get along pretty well.
Frequently Asked Questions
Ready to Connect?
If you made it this far, the setup is genuinely 90 seconds. Add the config block, restart Cursor, authorize, done. And if you run into any issues or want to talk about what you are building with this data, reach out to me directly. I am always interested in what developers and investors are doing with programmatic access to our property data. Some of the coolest tools I have seen started as side projects in exactly this kind of setup. And I’m not exactly a professional developer myself (lighting designer turned realtor turned… whatever I am now), so I appreciate when people show me what they built.
Be safe, be good, and be nice to people.
