ZBS Index What actually exists in applied AI, with the source next to it

mcp server

realtystack-mcp

U.S. real-estate data: property records, AVM value + rent estimates, sale/rental listings.

Description as published by the maintainer. Source

  • version 1.0.0
  • active

active — Registry entry last updated 2026-08-01.

What this server can do

6 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

avm_rent(address, daysOld, bedrooms, latitude, bathrooms, compCount, longitude, maxRadius, propertyType, squareFootage, lookupSubjectAttributes)
Run RentCast's automated model for long-term (12-month lease) rent and return a point rent estimate, a rentRangeLow/rentRangeHigh band, the resolved subjectProperty, and comparables[] — recent comparable rentals each scored with distance and correlation. Same subject-pinning rules as avm_value (address or latitude+longitude, plus optional subject attributes). Cached 6h upstream.
avm_value(address, daysOld, bedrooms, latitude, bathrooms, compCount, longitude, maxRadius, propertyType, squareFootage, lookupSubjectAttributes)
Run RentCast's automated valuation model for a subject property and return a point price estimate, a priceRangeLow/priceRangeHigh band, the resolved subjectProperty, and comparables[] — recent comparable sales each scored with a distance (miles) and correlation (0-1 similarity). Pin the subject with either address or latitude+longitude; when subject attributes are unknown, supply propertyType/bedrooms/bathrooms/squareFootage (or leave lookupSubjectAttributes true to have RentCast fill them). Cached 6h upstream.
get_property(id)
Full detail for a single property record, keyed by its RentCast id (the same id returned on every search_properties, avm_value, avm_rent, and listings record). Returns 404 if no property matches the id. Cached 24h upstream. Required: id.
search_properties(city, limit, state, offset, radius, address, lotSize, zipCode, bedrooms, latitude, bathrooms, longitude, yearBuilt, propertyType, saleDateRange, squareFootage, includeTotalCount)
Search normalized U.S. property records (owner, structural attributes, tax assessments, tax + sale history) by location. Pin a location one of three ways: a full address, a city+state(+zipCode), or a latitude+longitude point with a radius (miles). All other parameters narrow the result set. Records are cached 24h upstream, so meta.cached may be true on repeat queries.
search_rental_listings(city, limit, price, state, offset, radius, status, address, daysOld, lotSize, zipCode, bedrooms, latitude, bathrooms, longitude, yearBuilt, propertyType, squareFootage, includeTotalCount)
Return a page of long-term (12-month lease) rental listings — same record shape as search_sale_listings (monthly price is the asking rent), but each record is tagged listingKind:"rental-long-term". Same location-pinning rules and 30-minute upstream cache as the sale-listings endpoint.
search_sale_listings(city, limit, price, state, offset, radius, status, address, daysOld, lotSize, zipCode, bedrooms, latitude, bathrooms, longitude, yearBuilt, propertyType, squareFootage, includeTotalCount)
Return a page of for-sale listings (list price, status, days on market, MLS name/number, listing agent + office contact, and price/status history) for a location. Same location-pinning rules as search_properties (address, city+state(+zipCode), or latitude+longitude+radius). Each record is tagged listingKind:"sale". Listings move faster than records, so these are cached only 30 minutes upstream.

Last successful function declaration observed on . Source: https://realtystack-mcp.vercel.app/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://realtystack-mcp.vercel.app/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
Latest published version 1.0.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-08-01 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-08-01 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
mcp tools declared 6 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe realtystack-mcp.vercel.app
mcp endpoint status ok The server listed 6 functions when asked. as of probe realtystack-mcp.vercel.app

Where to get it

Also from isaiahdupree

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. Tools declared by the MCP server at https://realtystack-mcp.vercel.app/mcp — realtystack-mcp.vercel.app, observed , trust tier 1.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.