Homes MCP vs Housing Intel
A side-by-side look at the Homes MCP and Housing Intel MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Homes MCP for real estate work as a local process; choose Housing Intel for real estate as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Homes MCP when
- You need dedicated capabilities in the Real Estate domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: other.
- You want tools like
homes_search_properties, homes_get_property, homes_calculate_mortgage.
Choose Housing Intel when
- You need dedicated capabilities in the Real Estate domain.
- You prefer a local stdio subprocess transport.
- You want tools like
case_shiller_metro_compare, housing_market_snapshot, housing_property_report.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Real Estate | Real Estate |
| Quality signal | 63/100 · Good | 61/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | other | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 1 |
| Directory activity | 2 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 21 | 10 |
| Full listing | View Homes MCP | View Housing Intel |
Tools & capabilities
Homes MCP tools 21
homes_search_propertiesSearch homes.com listings by free-text location (city, ZIP, neighborhood). Optionally filter by property_type (single_family/condo/townhouse/land/mobile/multi_family), listing_type (for_sale/sold/for_rent/open_houses/new_construction), and sort (newest). Slugifies the location into homes.com's URL routing (e.g. 'Atlanta, GA' + condo + for_sale → /atlanta-ga/condos-for-sale/). Parses the embedded Schema.org JSON-LD to return each listing's address, price, beds/baths, sqft, primary photo, listing agent + brokerage, and the homes.com property URL. `location` is required and must contain Latin letters or digits — a blank or unsluggable location (e.g. only punctuation or non-Latin script) is rejected with an error rather than returning an empty result. KNOWN CAP: homes.com server-renders ~40 listings per page; the response carries `truncated: true` + `total_estimated` when the market has more. To enumerate a busy market, price-band or sub-area your search until each segment fits under the cap. Read-only; safe to call repeatedly.homes_get_propertyFetch a property's full homes.com record. Pass `url` — the full property detail URL (e.g. from a homes_search_properties result's `url` field). Parses the page's Schema.org JSON-LD plus DOM-side sections to return address, lat/lng, beds/baths, sqft, year built, price, status, listing agent + brokerage, highlights, estimated monthly payment, total views, Matterport tour URL, floorplan URLs, schools, HOA fee, lot_size_sqft plus the derived lot_size_acres (round(lot_size_sqft / 43560, 2); both null — never 0 — for condos and listings with no lot), parking, heating/cooling, MLS ID/source, and date posted/modified. Also returns `extracted_features` (lake_front, hot_tub, basement, furnished, dock, community) derived server-side from the listing description so callers don't have to keyword-parse marketing prose. Pass `include_price_history: true` to inline the same data `homes_get_property_history` returns (`listing_events`, `ownership_events`, `lien_events`, `events_normalized`) under `price_history`. Pass `include_tax_history: true` to inline `homes_get_tax_history` records under `tax_history`. Both are off by default; opting in costs nothing extra over the dedicated tools (same page fetch). The raw `description` is omitted by default; pass `include_description: true` to opt back in. `listing_agent` carries name / job title / profile url only; pass `include_agent_contact: true` for the agent's telephone and email. Read-only; safe to call repeatedly.homes_calculate_mortgageLocal-only mortgage payment calculator. Returns a full PITI breakdown (principal + interest, property tax, insurance, HOA, PMI) and total interest over the life of the loan. No network call — fully deterministic, safe to use for scenario comparison without burning a fetch. Provide either `down_payment` OR `down_payment_percent`; defaults to 20%. Property tax can be given as `property_tax_annual` or `property_tax_rate` (% of home price). PMI applies automatically when LTV > 80% and `pmi_rate` is provided.homes_compare_propertiesFetch 2 or more homes.com properties and align their facts side-by-side. Each target supplies a `url` — the full homes.com property URL (e.g. from a homes_search_properties result's `url` field). Returns the full per-property record (with server-side `extracted_features`, `hoa_monthly_usd`, `days_on_market`, `price_drop_*`, `lot_size_sqft` + the derived `lot_size_acres`, and `portal_url_hyperlink`). Per-target errors are captured per-row — one bad target will not fail the whole call: a failed row carries `status` = `error_kind` (`timeout` / `bridge_down` / `protocol` / `other`) plus `retryable` and `error`, and the envelope reports `count` / `ok` / `errored`. Calls are concurrent and bounded by an overall deadline: any row still unsettled comes back `status: "pending"` (retryable) with a top-level `pending` count — re-run just those targets. The raw `description` is omitted by default; pass `include_description: true` to keep the marketing prose. `listing_agent` omits the agent's telephone/email unless `include_agent_contact: true`. The cross-row `summary` table duplicates per-property fields (~30% of response weight); it is OPT-IN via `include_summary: true`.homes_calculate_affordabilitySolve for the maximum home price you can afford under the standard 28/36 DTI rule. Inputs: monthly income, recurring monthly debts (car loans, student loans, etc.), down payment, interest rate, and optional property-tax rate / insurance / HOA / loan term. Output: max home price, the binding constraint (front-end vs back-end), and the full PITI breakdown at that price. Same math across the realty MCP cohort (@chrischall/realty-core). No network — pure local math.homes_get_property_photosThe full photo gallery for a homes.com listing. homes.com's JSON-LD only exposes one primary image, so this tool scrapes every <img> tag on the property detail page and filters to the homes.com CDN. Pass `url` — the full homes.com property URL or path (e.g. from a homes_search_properties result's `url` field). Returns `{ property_id, url, count, photos: [{ url, position, alt? }] }`. Read-only; safe to call repeatedly.homes_healthcheckRound-trips a small public www.homes.com URL (/robots.txt) through ContextMint Bridge (your signed-in browser tab) and returns diagnostics: the bridge's role (host/peer/null), port, version, the extension link (linked / pair pending / not attached / never answered), the elapsed round-trip time, and a plain-English hint distinguishing 'bridge never came up' from 'extension not connected' from 'this browser can't serve a capability' from 'real www.homes.com-side problem'. Read-only, no auth required. Call this when a real tool fails and you want to know which hop broke.homes_get_property_historyDEPRECATED — prefer `homes_get_history` (combined timelines + tax) or `homes_get_property({ url, include_price_history: true })`. Same data, fewer round trips. Will be removed in a future major version. Three timelines for a homes.com property in one call: `listing_events`, `ownership_events`, `lien_events`. Also returns `events_normalized` mapped onto the cross-MCP enum. Each `events_normalized` row is `{ date, type, price?, price_change_pct?, list_to_sale_pct? }` — `price_change_pct` only on `PriceChange` rows; every other row carries homes.com's "List to Sale" figure as `list_to_sale_pct` (e.g. the sale-to-list ratio on a `Sold` row), never as a price change.homes_get_tax_historyDEPRECATED — prefer `homes_get_history` (combined timelines + tax) or `homes_get_property({ url, include_tax_history: true })`. Same data, fewer round trips; note that `homes_get_history` returns the tax array as `tax_records` (not `records`). Will be removed in a future major version. Year-by-year property-tax records: tax paid, total assessed value, land/improvement split.homes_get_historyCombined history endpoint — replaces `homes_get_property_history` + `homes_get_tax_history` with a single fetch. Returns `{ property_id, url, listing_events, ownership_events, lien_events, events_normalized, tax_records }`. Pass `url` — the full property detail URL. Series are `[]` when the listing doesn't carry that section. Cross-MCP-normalized `events_normalized` carries the same enum across siblings (Listed/PriceChange/Pending/Contingent/Sold/Withdrawn/Relisted/Delisted). Each `events_normalized` row is `{ date, type, price?, price_change_pct?, list_to_sale_pct? }` — `price_change_pct` only on `PriceChange` rows; every other row carries homes.com's "List to Sale" figure as `list_to_sale_pct` (e.g. the sale-to-list ratio on a `Sold` row), never as a price change. Read-only; safe to call repeatedly.homes_get_nearby_listingsScrape the nearby-links section of a homes.com detail page (the tabbed list of `<ul id="nb-Property">` near the bottom of the page) and return the nearby active listings. Pass `url` (the property whose neighborhood to inspect). By default returns the For Sale tab; pass `include_rentals: true` to also include the Rentals tab. Optional `limit` caps the count. Returns `{ property_id, url, count, listings: [{ property_id, url, address?, tab }] }`. Note: the nearby section is a curated cross-link list, not a comparable-sales set — only URL + address are exposed (no price/beds/baths/sqft/photo). To enrich a row, call `homes_get_property` on its url. Read-only; safe to call repeatedly.homes_get_market_reportFetch homes.com's recently-sold listings for a city/ZIP/neighborhood and derive a market summary: count, median sale price, and average $/sqft across the sample. Pass `location` — free-text (e.g. 'Brooklyn, NY', '30311'). `location` is required and must contain Latin letters or digits — a blank or unsluggable location (e.g. only punctuation or non-Latin script) is rejected with an error rather than returning an empty result. Returns `{ region, slug, sold_summary, sample_sold }`. Note: homes.com's sold page typically returns ~40 recent listings — this is a sample-based summary, not an exhaustive market index. Read-only.- +9 more on the listing page
Housing Intel tools 10
case_shiller_metro_compareCompare Case-Shiller home price indices across multiple US metros in one call (the 20-city composite). For each metro returns latest level, 3-month change, 12-month change, all-time peak, drawdown from peak, and a softening flag. Output also ranks metros softest → strongest. Use for "which metros are softening", "Case-Shiller for [list of cities]", "compare housing prices in X, Y, Z" queries — picks the right per-metro FRED series IDs (DNXRSA, PHXRSA, TPXRSA, etc.) so callers don't have to. Available metros: Atlanta, Boston, Charlotte, Chicago, Cleveland, Dallas, Denver, Detroit, Las Vegas, Los Angeles, Miami, Minneapolis, New York, Phoenix, Portland, San Diego, San Francisco, Seattle, Tampa, Washington DC. NOT A CURRENT-MARKET READ: Case-Shiller is monthly, published on a roughly two-month lag, and each value is a three-month moving average — so the newest observation is typically 90-120 days old and describes a trailing quarter. The `freshness` block states the exact age of the call you made.housing_market_snapshotGet national housing market overview: mortgage rates, housing starts, Case-Shiller index, unemployment, construction employment. Optionally add metro-level prices (e.g., "Denver", "Atlanta"). For comparing Case-Shiller across multiple metros use case_shiller_metro_compare instead. THE COMPONENTS DO NOT SHARE A DATE — they are weekly, monthly and quarterly official statistics, each published on its own lag, so one call can span months of vintages. `freshness` states the span in days and names the oldest component; read it before comparing components against each other.housing_property_reportAnalyze a property by address and zip code. Returns valuation estimate, sales history, tax assessment, and detailed characteristics.housing_rental_analysisEvaluate rental investment potential by address and zip code. Returns estimated rent, fair market rents, and CPI rent trends.housing_affordability_checkCheck housing affordability in a market. Returns mortgage rate, median price, monthly payment, required income, and HUD limits. Optionally specify metro (e.g., "Denver"). The inputs are official statistics on DIFFERENT cadences — a weekly mortgage rate against a quarterly median price — so the monthly payment is an illustrative ratio of published figures, not a live quote. `freshness` states the span and the age of each input.housing_employment_outlookAssess labor market health for housing demand. Returns employment, construction jobs, residential building employment, unemployment rate, and job openings. All BLS monthly releases; each series carries its own `observation_date` and `cadence` (JOLTS runs an extra month behind CES/LAUS), and `freshness` states the span. `snapshot_date` is the call date, not the data date.housing_signal_scanScan 45+ housing indicators for anomalies and reversals. Flags unusual moves across rates, starts, sales, prices, wages, unemployment, and rent. Each signal carries its own `observation_date` and `cadence` — series here span weekly (mortgage rate) to quarterly (median sales price), and Case-Shiller is additionally a 3-month moving average, so "turned negative" does not mean "this month" for every series. `freshness` states the full span and the oldest component.housing_mortgage_historyFreddie Mac Primary Mortgage Market Survey — the weekly US mortgage INTEREST rate (the annual percentage borrowers pay on a home loan, e.g. 6.5%), back to 1971. This is the borrowing cost paid by home buyers. Returns the latest snapshot, a time series for the requested window, and min/max/avg stats. Sourced from Freddie Mac directly (not FRED), ingested weekly by the Pipeworx data pipeline.housing_market_screenRank US metros for rental cash flow in ONE call — the "which markets are best for a landlord" view. Returns metros sorted by gross rent yield = (Zillow median monthly rent × 12) ÷ Zillow typical home value. No per-metro orchestration and no API key. Use for "best/worst rental markets", "highest-yield metros", "where does rent go furthest vs. home prices". Tune with direction (top = highest yield / best cash flow, bottom = lowest), limit, and optional home-value bounds. rent_as_of and home_value_as_of are two independent Zillow queries and can land on different months; `freshness` says whether they matched this call.housing_metro_demandDemand + rent-durability signals for a shortlist of US metros in ONE call — population & 5-year growth, renter share, median household income, and unemployment, straight from Census ACS. Deterministic by metro (CBSA-keyed) — NO FRED series-ID guessing. Pass `metros` ("City, ST", e.g. the top results from housing_market_screen). This is the Stage-2 "is the demand real?" filter on a yield shortlist — high yield in a shrinking metro is a trap. No API key needed. HIGHEST-LAG SOURCE IN THIS PACK: figures are a Census ACS 5-YEAR rolling average (currently 2018-2022, released Dec 2023) — for structural demand, not a current-quarter read. `freshness` states the exact age.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Homes MCP
{
"mcpServers": {
"homes-mcp": {
"command": "npx",
"args": [
"-y",
"homes-mcp"
]
}
}
}
Housing Intel
{
"mcpServers": {
"housing-intel": {
"command": "npx",
"args": [
"-y",
"@pipeworx/mcp-housing-intel"
]
}
}
}
Frequently asked questions
Homes MCP is categorized under Real Estate and uses a local stdio subprocess. Housing Intel belongs to Real Estate and uses a local stdio subprocess. Pick Homes MCP for real estate work and Housing Intel for real estate.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Homes MCP is listed as free. Auth: other. Housing Intel has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add homes-mcp and housing-intel as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Homes MCP has a quality signal of 63/100 (Good) with 2 views, 0 installs and 0 GitHub stars. Housing Intel has 61/100 (Good) with 1 views, 0 installs and 1 GitHub stars.