Ed Neuhaus 
Cline just crossed 3.6 million installs in the VS Code marketplace. That makes it the most popular open-source AI coding agent available, and it runs right inside the editor most developers already use every day. So when we built the Austin MLS MCP connector, Cline compatibility was high on the list. One remote server config and you can search Austin real estate listings from NeuhausRE.com without ever leaving VS Code. Listings, comps, market stats, the same property data displayed on our website, just delivered inside your coding environment.
Sounds like it should be complicated right. It’s not. The setup takes about two minutes through Cline’s built-in Remote Servers UI, and once you’re connected you can ask your AI agent to pull listings in 78738 or run comps on a property in Bee Cave while you’re in the middle of writing code. No tab switching. No separate API console.
What Cline Is (And Why It Matters for This)
If you’re here you probably already know Cline. But just in case someone wandered in from a real estate search: Cline is an open-source AI coding agent that lives inside VS Code as an extension. Unlike Cursor (which is its own standalone editor built on VS Code), Cline plugs into your existing VS Code setup. You keep all your extensions, your keybindings, your themes, everything. Cline just adds an AI agent that can read your codebase, create files, run terminal commands, and connect to external data through 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: MCP is a standard protocol that lets AI tools talk to live data sources. Instead of copy-pasting data from a website into your editor, the AI agent pulls it directly.
Eric Ries built the whole Lean Startup philosophy around this idea of shortening feedback loops. Build, measure, learn, repeat. Having live property data inside your coding environment is exactly that. You write a function, test it against real listings, iterate. No waiting, no context switching, no stale data. The loop gets tighter.
Why You’d Want Austin Property Data Inside Cline
Ok lets be practical about who actually benefits from this.
Developers building property tools. If you’re creating a property search app, an investment calculator, or anything that touches listing data, you need real data to test against. And you need it while you’re coding, not in a separate browser tab you keep alt-tabbing to. With Cline connected to the NeuhausRE MCP connector, you can ask your AI agent to search listings, pull details on a specific property, or grab market stats for a zip code right there in the VS Code chat panel. Then use those results immediately in whatever you’re building.
Investors who write scripts. I know more RE investors who code than most people would expect. Python scripts to screen deals, calculate cash-on-cash returns, filter by days on market. If that’s you, connecting Cline to our MLS data turns VS Code into a deal analysis machine. Ask for every listing under $700,000 in Lakeway with 4+ bedrooms and get real results you can pipe straight into a pandas DataFrame.
Agents building internal tools. This one is close to home for me. At Neuhaus Realty Group I’ve been building my own tools for years because the off-the-shelf stuff never quite does what I need (a story most agents who’ve tried to customize their CRM know well right). Cline with MLS access means you can prototype and test against live data as you build. No mocking, no sample data, no guessing whether your function will work when it hits real listings.
And honestly if you just spend most of your day in VS Code and happen to be house hunting in Austin, this is the laziest possible way to browse listings. I mean that as a compliment.
Step-by-Step: Connecting Cline to Austin Real Estate Data
Here’s the actual setup. Cline gives you two ways to do this: the GUI method (easier) and the JSON method (faster if you’ve done this before). I’ll show both.
Method 1: Remote Servers UI (Recommended)
Step 1: Open the MCP Servers Panel
In VS Code, click the Cline icon in your sidebar (looks like a terminal with a sparkle). At the top of the Cline panel, you’ll see an MCP Servers icon. Click it. This opens the MCP server management interface where you can add, remove, and configure servers.
Step 2: Go to Remote Servers
Click the “Remote Servers” tab. This is where you add MCP servers that run on the web (as opposed to local servers running on your machine). Our MLS server is remote, so this is where we want to be.
Step 3: Add the NeuhausRE MCP Server
Fill in the fields:
- Server Name: austin-mls
- Server URL:
https://mls.neuhausre.com/mcp - Transport Type: Streamable HTTP
Click “Add Server” and you’re in. That’s the whole configuration.
Step 4: Authenticate
The first time Cline connects, it kicks off an OAuth flow. Your browser opens with a quick signup form asking for your name, email, and phone number. Fill it out, authorize, done. Cline stores your credentials securely and reconnects automatically next time you open VS Code. You won’t need to authenticate again unless you delete the server or your token expires. No big deal right.
Method 2: Edit the JSON Config Directly
If you prefer editing config files (and lets be honest, if you’re using Cline you probably do), you can add the server directly to cline_mcp_settings.json.
Open the command palette (Cmd+Shift+P on Mac, Ctrl+Shift+P on Windows) and search for “Cline: MCP Settings.” That opens the config file. Add this block inside the mcpServers object:
{
"mcpServers": {
"austin-mls": {
"url": "https://mls.neuhausre.com/mcp",
"type": "streamableHttp"
}
}
}If you already have other MCP servers configured, just add the "austin-mls" entry to your existing mcpServers block. Save the file, and Cline picks it up automatically. You’ll get the same OAuth prompt on first connection.
One thing I like about Cline specifically: you can toggle servers on and off with a switch in the MCP Servers panel. So if you only want MLS access during certain projects, just flip it off when you don’t need it. Small detail, but nice.
What You Get Once Connected
After authenticating, Cline has access to four tools through the MCP server:
search_listings. Find active listings by city, zip code, neighborhood, price range, beds, baths, square footage, features. Ask in natural language and Cline figures out which parameters to pass.
get_listing. Full details on a specific property. Photos, descriptions, tax history, HOA info, school assignments. Everything the MLS has.
get_comps. Closed-sale comparables by address, radius, and date range. This is what agents use to price homes and what smart buyers use to make informed offers. Available on the Active Buyer tier.
get_market_stats. Median prices, inventory levels, days on market, price-per-square-foot trends by city or zip code. Also Active Buyer tier.
The data is the same regardless of which AI client you use. Same MCP server, same endpoint, same results. Whether you’re in Cline, Cursor, Claude Desktop, or Perplexity, the property data comes from the same place: the live MLS feed that powers NeuhausRE.com.
Example Prompts to Try
So you’re connected. Here are some real prompts you can drop into Cline’s chat to see what comes back. These are the kinds of questions I actually ask when I’m evaluating a market or helping a client.
Searching for listings:
- “Show me all active listings in Bee Cave under $900,000 with at least 3 bedrooms”
- “Find homes in Westlake with a pool that have been on the market more than 30 days”
- “What’s available in 78746 between $500K and $800K?”
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 Dripping Springs over $600K in the last 90 days”
Market stats:
- “What’s the median home price in Lakeway right now?”
- “Show me inventory levels and days on market for zip code 78738”
- “Compare median prices in Dripping Springs vs Bee Cave”
But here’s where Cline gets interesting compared to the other clients. Because Cline is a coding agent, you can take those results and immediately act on them programmatically. Ask Cline to search listings, then in the same conversation ask it to write a Python script that filters the results by price per square foot. Or have it build a quick dashboard. Or generate a CSV export. The data and the development environment are in the same place, which is something you can’t really do in Perplexity or Claude Desktop.
Building Things With Live MLS Data
This is the section that’s really for the developers and the investors-who-code crowd. If you just want to browse listings from VS Code, the prompts above are all you need. But if you want to build on top of this data, here’s where it gets fun.
Investment screening scripts. Have Cline write a script that pulls all listings in a zip code, calculates estimated monthly payment at current rates, and flags anything where the rent-to-price ratio exceeds a threshold you set. I’ve seen investors build these in about 20 minutes with Cline doing the heavy lifting on the code. You just describe what you want and iterate.
Comp analysis tools. Ask Cline to build a function that takes an address, pulls comps within a radius, and outputs a summary with median sale price, price per square foot range, and days on market distribution. Then wrap it in a simple CLI tool you can reuse. Not a bad afternoon project.
Market monitoring dashboards. Want to track median prices in 78704 over time? Have Cline write a script that calls get_market_stats weekly and logs the data to a local database. Then build a chart. Or just have Cline build the chart. Either way you end up with a personal market tracker that uses real MLS data, not Zillow estimates.
I’m not exactly a professional developer myself (lighting designer turned realtor turned… whatever I am now), so I appreciate when tools like Cline lower the bar. You don’t need to memorize API endpoints or write boilerplate HTTP clients. You tell the AI agent what you want, it calls the MCP tools, and you get results. Then you tell it to write the code that does it automatically next time.
Free Access and the Active Buyer Retainer
The NeuhausRE MCP connector has a free tier that works right now. You get 10 results per search, 10 queries per hour, and 100 per month. That’s plenty for exploring the market, testing code against real listings, and casual property research.
If you’re actively searching for a home in Austin, we also offer an Active Buyer retainer at $200/month. That bumps your limits to 50 results per search, 200 queries per hour, and 10,000 per month, plus it unlocks comps and market stats. But I want to be clear about what this actually is. It’s a buyer representation retainer for my services at Neuhaus Realty Group. Nineteen years of Austin market experience, property tours, offer strategy, negotiations. The full agent relationship. The MLS access is one of the things that comes with that relationship, and the entire $200 gets credited back to you at closing if you purchase through us.
So the data itself is free either way. The retainer is for buyers who want priority service, higher volume, and an experienced agent in their corner.
Cline vs Cursor vs Claude Desktop
If you’ve read our Cursor guide or our Claude Desktop guide, the natural question is: what’s different?
Same MCP server. Same data. Same endpoint. The difference is what each tool is built for.
Cursor is a standalone editor. You get a tighter integration (MCP is baked into the editor itself), but you have to leave VS Code behind. Some people love Cursor. Some people have 47 VS Code extensions they’re not willing to give up.
Claude Desktop is for conversation and analysis. Great for “help me understand this market” or “compare these three properties for me.” Less great for writing code against the results.
Cline is for people who want to stay in VS Code and still have an AI agent that can code AND pull live data. It’s the best option if you’re building tools on top of the MLS data, because Cline can write the code and test it against real listings in the same session. The full list of supported AI clients is on the main connector page.
And if I’m being honest, the “right” client is whichever one you already use. The MCP protocol is the same everywhere. Pick the tool you’re comfortable in and connect it. Kevin Kelly’s whole insight about the internet was that distribution shouldn’t dictate access. Same idea here. The data should meet you where you work.
Why I Built This
I get asked about this enough that I’ll just say it. 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’s slow if you’re trying to do serious analysis or build something on top of it.
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 about why that approach is broken). The same listings, the same comps, the same market data, just delivered through your AI tools instead of a web browser.
And honestly the people who connect Cline to MLS data tend to be the kind of people I enjoy working with. They do their own research. They run their own numbers. They show up to a conversation with an agent already knowing what they want. Those are my favorite clients. We tend to get along.
Frequently Asked Questions
Ready to Connect?
If you made it this far, the setup is genuinely two minutes. Open Cline’s MCP Servers panel, add the remote server URL, authenticate, done. And if you run into anything weird or want to talk about what you’re building with this data, reach out to me directly. I’m always curious what developers and investors build when they get programmatic access to real property data. Some of the most interesting tools I’ve seen started as side projects in exactly this kind of setup.
Be safe, be good, and be nice to people.
