What it does
Zillow Comp Market Analyzer is a Level-2 MCP agent for real estate professionals. It collects comparable sales from Zillow (last 90 days, filtered by property type, square footage, bedrooms and age), deterministically computes price per square foot, average days on market, and list-to-sale ratio, derives a low/mid/high recommended list price range, and can write the CMA table to Google Sheets. An LLM synthesizes the narrative summary; a deterministic template fallback guarantees output even offline. Guardrails include a minimum-5-comps check, outlier removal, prompt-injection scanning, and a decision-support-not-investment-advice disclaimer. Built for real estate agents and appraisers who need a fast, data-driven comparative market analysis instead of manually pulling comps.
Example prompts
- Run a full CMA for a 3-bed house at 123 Main St, Springfield IL
- Summarize comp metrics for zip code 62701
- What's the market condition for this neighborhood right now?
- Estimate a recommended list price range for a 1900 sqft home
Tools (8)
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Run the full Zillow CMA pipeline: fetch comp data, analyze price/sqft + DOM + list-to-sale ratio, synthesize a narrative summary, return the complete CmaResult JSON.
- analyze_comps — Given a RawData object (target + all_comps array), run pure deterministic CMA analysis and return CmaResult + findings. No LLM.
- get_comp_summary — Quickly summarize comp metrics for an address/zip: avg price/sqft, avg DOM, list-to-sale ratio and market condition.
- check_market_condition — Classify market condition (seller/balanced/buyer) from avg_days_on_market and list_to_sale_ratio.
- estimate_price_range — Estimate a recommended list price range (low/mid/high) from comps data and target sqft.
- list_capabilities — List the agent's available tools and capabilities.
- plan_inputs — Plan/brainstorm the inputs for a tool: returns questions, schema and a ready-to-edit example.
- discover_intent — Understand your goal and co-design the exact input via clarifying questions before running.
What you'll need to connect
This agent will ask you for the following. You enter them when you connect — they're encrypted and never shared with the creator.
- Zillow API Key · optionalZillow/Bridge Data Output API key for comp sales data. Required for live data; mock fixtures used without it.Get this from bridgedataoutput.com's account or API settings.Paste the value as a single line.Only sent to: api.bridgedataoutput.com, www.zillow.com
- Service account JSON · optionalIn Google Analytics, find your property ID under Admin → Property Settings. Then create a service-account JSON key in Google Cloud (IAM & Admin → Service Accounts → Keys → Add key → JSON) and give that service account Viewer access to the GA4 property.Paste the full JSON of your service-account key file (not a file path). FindAgent stores it securely and gives the agent a file path to it.Only sent to: sheets.googleapis.com, oauth2.googleapis.com
- Anthropic API Key · optionalOptional. Leave blank on a sampling-capable client to use the host model with no key.Create a key on the Anthropic Console API keys page (console.anthropic.com → API keys).Paste the value as a single line.Only sent to: api.anthropic.com
How you're protected
FindAgent runs these safety checks on every agent automatically. They're always on and can't be turned off.
- Prompt-injection scanning
Every request is checked for known prompt-injection and jailbreak attempts before the agent runs. This is always on.
- Secret-leak scanning
Every response is scanned for leaked API keys, tokens, and other secrets before it reaches you. This is always on.
