@pipeworx/altos

Connect: https://gateway.pipeworx.io/altos/mcp · Install: one-click buttons

Tools: 6

Altos Research is the industry’s standard for weekly-cadence US real estate market statistics: median list prices, price reductions, days on market, inventory by ZIP / metro / state, broken out by property type (single-family, condo) and market quartile. Where MLS data is fragmented and lagged, Altos aggregates and publishes weekly.

Why this matters for AI agents

Most public housing data (Census ACS, FRED home price index) updates monthly or quarterly. Altos updates weekly with the data agents and lenders actually use to gauge market temperature. If an agent is answering “is this market hot or cold right now?” the Altos data is most fit-for-purpose.

Common flows:

• Metro stats. altos_market_stats({region: "us-co-denver"}) → median list, days on market, inventory, weekly trend.
• Property type filter. Same call with res_type: "single_family" or "condo".
• Quartile filter. quartile: "FIRST" to focus on the bottom-quartile market (entry-level), "FOURTH" for luxury.
• Multi-metro comparison. Iterate calls in parallel for a peer comparison.

Used by the housing_property_report and housing_market_brief compounds.

Auth

Altos is a paid commercial data product. Two paths:

1. BYO key: get an Altos partner key directly (commercial relationship), pass via _altosKey.
2. Pipeworx Housing Vertical: subscribe at pipeworx.io/account and Pipeworx fronts the relationship. No _altosKey needed.

The vertical option is the common case — most agents using Altos also want ATTOM, FRED, and BLS for housing analysis. Bundling them is cheaper than separate keys.

Region codes

Altos uses geo-coded region IDs:

Smaller geographies have noisier data — single-ZIP weekly stats can swing wildly with low listing counts.

Update cadence

Weekly, typically published Monday or Tuesday for the prior week’s data. Pipeworx caches with 24-hour TTL; intra-week, the same number is returned (Altos doesn’t intra-week update).

Common pitfalls

• List vs. sale price. Altos primarily tracks active listings — list price, days on market, price reductions. Sale prices and YoY-sale-price-change come from county records (ATTOM) and have longer lag. Don’t conflate “Altos median price” with “sold for.”
• Active inventory ≠ months-of-supply. Altos gives you the level; months-of-supply (a more interpretable metric) needs absorption rate too. Compute as inventory / monthly sales rate.
• Quartile semantics. Altos splits the market into 4 price quartiles per region. The first quartile is bottom 25%, fourth is top 25%. Quartile boundaries are recomputed each week.
• Property type changes coverage. Single-family is universally covered; condos exist in metros where condos are common (urban centers). Rural metros may return null for condo queries.
• “This week” gets revised. The most recent week is provisional and gets revised slightly the following week as more listings flow in. Don’t deploy production decisions on the most-recent-week number alone.

Tools

• altos_market_stats — Get current market snapshot for a region (e.g., “San Francisco, CA”). Returns inventory count, new listings, median price, days on market, and market action index.
• altos_inventory_trend — Track weekly inventory changes for a region (e.g., “Austin, TX”). Returns trends in inventory, new listings, days on market, median price, and price reductions.
• altos_active_listings — Search active property listings in a region (e.g., “Denver, CO”). Returns address, price, beds, baths, square footage, and listing status.
• altos_pending_sales — Find properties under contract in a region (e.g., “Miami, FL”). Returns address, price, beds, baths, and days pending.
• altos_new_listings — Get freshly listed properties (under one week on market) for a region (e.g., “Boston, MA”). Returns address, price, beds, baths, and listing date.
• altos_list_files — Browse downloadable regional real estate data files. Returns catalog with file names, formats, and descriptions.