Zillow MCP Server: Property Data for Claude, Cursor, and AI Agents

August 19, 2026 · 6 min read

Ask Claude "what's this house worth?" and it will reason beautifully about a number it doesn't have. Language models know everything about real estate except the actual data — current prices, Zestimates, what sold last month. The Model Context Protocol (MCP) fixed the plumbing problem: agents can call tools. What's left is giving them a tool worth calling.

apillow-mcp is that tool for Zillow property data: an MCP server that lets Claude Desktop, Claude Code, Cursor, Windsurf — any MCP-compatible agent — search listings and pull 50+ fields for any US property, live. Install to first query is about two minutes, and if you don't have an API key yet, the agent can sign itself up.

Install in two minutes

pip install apillow-mcp

Claude Desktop — add to ~/.claude/claude_desktop_config.json:

{ "mcpServers": { "apillow": { "command": "apillow-mcp", "env": { "APILLOW_API_KEY": "your_key" } } } }

Claude Code — one command:

claude mcp add apillow -- apillow-mcp

Cursor and Windsurf use the same JSON shape in their respective MCP config files. Full details are in the docs.

No API key? Let the agent get one

This is the part that surprises people. The server ships account tools alongside the data tools, so onboarding happens entirely inside the conversation:

# You say: "Sign me up for Apillow with adam@example.com" # The agent calls signup() and gets back: { "api_key": "zs_abc123...", "plan": "free", "monthly_limit": 50 } # And can immediately start querying: "Find 3-bedroom homes under $500K in Austin TX"

The free tier is 50 requests/month with every field included. When the quota runs out, the agent can call upgrade_plan() and hand you a Stripe checkout link — the payment page is the only step that ever touches a browser.

The tools

Tool What the agent can do with it
search_properties(query, type, max_items) "Homes for sale in Beverly Hills under $2M"
search_by_zip(zipcodes, type, max_items) "What's on the market in 44124?"
get_property_by_address(address) "What's 1874 Bromton Dr worth, and what did it last sell for?"
get_properties_by_addresses(addresses) "Pull data for every address in this spreadsheet"
get_property(zpid) / get_property_by_url(url) Lookups by ZPID or a pasted Zillow link
signup · check_usage · upgrade_plan Account lifecycle without leaving the chat

Every property tool returns the full record — price, Zestimate and Rent Zestimate, beds/baths, price and tax history, schools, photos, and sold data including the sale date — so the agent can answer follow-ups without another round-trip.

What agents actually do with it

Why this beats a scraping MCP server

Most "real estate MCP servers" you'll find in directories are hobby projects that scrape Zillow from your machine on every tool call. They work in a demo and then meet Zillow's anti-bot stack — PerimeterX fingerprinting, rotating page structures — from your residential IP. The failure mode is silent: the agent just starts getting empty results.

apillow-mcp is deliberately boring: a thin client over the same hosted API our REST customers use in production. The scraping, anti-bot handling, and off-market sold-data enrichment run on our infrastructure, monitored around the clock; your agent makes an authenticated HTTPS call. Nothing brittle runs locally, and your IP stays out of it.

Hobby scraper MCP apillow-mcp
Runs from your IPYes — blocks land on youNo
Sold data on off-market homesUsually missingIncluded (enriched)
Survives Zillow layout changesUntil the next oneProvider's problem, not yours
OnboardingClone, configure, praypip install, agent signs itself up
CostFree until it breaksFree tier; from $9.99/mo

Give your agent property data

pip install apillow-mcp — then ask your agent to sign you up. 50 free requests a month.

Read the MCP Docs

Related reading

Final takeaway

MCP made it trivial to hand an agent tools; the hard part was always the data behind them. A Zillow MCP server backed by a production API gives Claude, Cursor, and friends real property data — prices, Zestimates, sold history — with a two-minute install and an onboarding flow the agent runs itself. That last part still feels like the future every time.