Gaff Check vs Compass MCP
A side-by-side look at the Gaff Check and Compass MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Gaff Check for real estate work as a local process; choose Compass MCP 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 Gaff Check when
- You need dedicated capabilities in the Real Estate domain.
- You prefer a local stdio subprocess transport.
- You want tools like
resolve_location, planning_applications, sold_prices.
Choose Compass MCP when
- You need dedicated capabilities in the Real Estate domain.
- You prefer a local stdio subprocess transport.
- You want tools like
compass_search_properties, compass_get_property, compass_get_saved_homes.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Real Estate | Real Estate |
| Quality signal | 61/100 · Good | 61/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 8 | 0 |
| Directory activity | 1 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 8 | 18 |
| Full listing | View Gaff Check | View Compass MCP |
Tools & capabilities
Gaff Check tools 8
resolve_locationResolve a free-text Irish address or place name to geographic coordinates (WGS84 lat/lng), returning ranked candidate matches. Use this first when the user gives an address, street, townland, or place name in Ireland, to confirm the correct location before calling other gaff-check tools — every candidate echoes its full resolved name so you (and the user) can sanity-check the match. If you already have exact lat/lng coordinates, you do not need this tool. Geocoding uses OpenStreetMap Nominatim and is best-effort: rural addresses and new estates may match poorly, and Eircodes only resolve where OSM mappers happen to have added them (there is no licensed Eircode lookup — if the user has only an Eircode, ask for the address or an approximate location instead). The confidence score ranks candidates within one query; it is not an absolute probability. Coordinates are WGS84 decimal degrees.planning_applicationsFind Irish planning applications near a location, from the National Planning Application Database (all 31 local authorities, coverage back to ~2010, updated on varying cadences). Use this for property due diligence: pending or recent developments near a home (apartment blocks, roads, masts), extensions and attic conversions on the same street (precedents for what gets approved), and refusals that hint at site constraints. Returns per application: reference number, local authority, development description, address, status, decision with dates, distance in metres from the query point, and a link to the local authority's planning file where available. Provide either lat/lng (WGS84) or a free-text address (geocoded via OpenStreetMap; the resolved location is echoed back — verify it matches before drawing conclusions). Dates are ISO YYYY-MM-DD. The 'decided'/'pending' filter is based on whether a decision date is recorded; raw status strings vary by local authority and are returned verbatim. Coordinates of some older applications are approximate, and update lag differs by authority — absence of results is not evidence that nothing is planned.sold_pricesLook up actual sold prices of residential properties in Ireland from the official Property Price Register (PSRA), which records declared prices from stamp-duty filings since January 2010. Use this to see what properties actually sold for near a property of interest: filter by county (required — the register is organised by county), a free-text address fragment (e.g. a street or estate name), an Eircode routing key (first 3 characters, e.g. 'D06' — only present on more recent records), a date range, and/or a price range. Returns per sale: date, declared price in EUR, address as recorded, Eircode where recorded, new vs second-hand, and flags for not-full-market-price and VAT-exclusive sales. Results are newest first. Know the data's limits: addresses are free text typed from stamp-duty returns — spelling varies, many records lack Eircodes, and address matching is substring-based, so try street name alone before street + number. There is no floor area, so price-per-square-metre cannot be derived. Prices on new builds are often VAT-exclusive (flagged), and declared-price errors exist in the register. This tool reports records, not valuations. If the user has no county, ask them (or infer it from the address) before calling.radon_riskGet the EPA's radon risk classification for the area containing a location in Ireland. Radon is a naturally occurring radioactive gas and the second biggest cause of lung cancer in Ireland after smoking. Use this during property due diligence to learn the area's banding from the EPA Radon Risk Map: the result echoes the EPA's own wording ("About 1 in N homes in this area is likely to have high radon levels", where N is 5, 10 or 20 — lower N means higher risk) plus a high_radon_area flag (true for the 1-in-5 and 1-in-10 bands, the ≥10% threshold Ireland uses to designate High Radon Areas, which carry legal testing duties for workplaces). This is an area-level prediction from measurement and geological data — it is NOT a measurement of any specific home. The EPA's standing advice ships in every response: any home anywhere can have high radon regardless of banding, the only way to know is to test, and testing is cheap (~€50). Provide lat/lng (WGS84) or a free-text address (geocoded; resolved location echoed back).zoningGet the generalised land-use zoning for a location in Ireland, from the Myplan.ie composite of all current local authority development plans. Use this in property due diligence to learn what the land is zoned for — residential, agricultural, open space, industrial, mixed use, etc. Zoning tells you what could be built there (or next door), whether a site has development potential, and whether a use is likely permissible. Returns the generalised zone type (standardised across authorities, e.g. 'Existing residential'), the local authority's own original zone label and objective text, the development plan name with its validity dates, and a link to plan documents where available. Provide lat/lng (WGS84) or a free-text address (geocoded; resolved location echoed back). Important: generalised zoning is a standardised simplification that complements but does NOT replace the statutory development plan — zone boundaries are generalised, and specific objectives, conditions and designations (protected structures, flood zones, SACs) live in the written plan. Verify anything decision-critical against the local authority's plan via the link. Points on unzoned land (much of rural Ireland outside town plans) return no records; that means no zoning objective is mapped, not that development is impossible.flood_riskCheck mapped flood context for a location in Ireland: groundwater flood probability (high/medium/low), maximum historic groundwater flooding, and observed winter 2015/2016 surface-water flooding, from Geological Survey Ireland's 1:20,000 mapping. Use this in property due diligence. For each layer you get: whether the point itself lies inside a mapped extent (at_point), how many extents fall within the search radius, and the distance in metres to the nearest one. Groundwater flooding (turloughs, high water tables) is a distinct hazard from river or coastal flooding and matters especially in karst limestone areas of the west and midlands. CRITICAL LIMITATION — this tool does NOT check river (fluvial) or coastal flood models. The OPW's national flood extent datasets are licensed CC-BY-NC-ND, which forbids serving derived query results, so results include unchecked entries for them pointing to the OPW's official viewer (floodinfo.ie) where the user can view all flood maps for the location. A property can be at serious river or coastal flood risk while showing nothing in this tool's results. Never interpret empty results as "no flood risk": mapping is not exhaustive, pluvial (rain) flooding is not mapped at all, and the fluvial/coastal layers are not queried. Absence of a mapped extent means exactly that and no more. Provide lat/lng (WGS84) or a free-text address (geocoded; resolved location echoed back). Insurance decisions use different, private data — this tool says nothing about insurability.ber_contextGet Building Energy Rating (BER) context for an area of Ireland: the distribution of BER grades (A1 best … G worst) among certified dwellings in a county or Dublin postal district, optionally narrowed to a construction era, plus current SEAI retrofit grant amounts. Use this to answer "what energy rating is typical for a house of this age around here?" and "what upgrade grants exist?" during property due diligence. Data is CSO statistics aggregated from BER certificates published since 2009 — e.g. 1978-1999 houses in Co. Galway cluster around C/D, while 2015+ builds are overwhelmingly A-rated. Areas accepted: the 26 counties, the cities (Dublin/Cork/Galway/Limerick/Waterford), or Dublin postal districts ('Dublin 9', 'D6W'). Construction periods: 1700-1977, 1978-1999, 2000-2004, 2005-2009, 2010-2014, 2015-2019, 2020-2024, 2025-2029. THIS TOOL CANNOT TELL YOU A SPECIFIC HOME'S BER — never present the area distribution as the property's rating. A home's actual BER is on its certificate: the seller/agent must provide it, or it can be looked up on SEAI's public register (link included in every response) with the BER number or MPRN. Note also the statistics' bias: only dwellings that needed a certificate (sold, rented, grant-aided, or new since 2009) are counted, so old housing stock that never transacted is under-represented and its true typical rating is likely worse than shown. Grant amounts are a static reference with a last-verified date — confirm on seai.ie before financial decisions.recorded_crime_contextGet recorded-crime context for the Garda sub-district containing an Irish location, using official CSO counts and current Garda administrative boundaries. Use this for factual questions such as "what categories of crime have been recorded in this wider Garda area?" or to supply category-specific values for a choropleth. It returns annual counts, a pooled annual average, rates per 1,000 Census 2022 residents with approximate 95% Poisson intervals, and optionally the latest four-quarter Garda Division trend. Provide WGS84 lat/lng or a free-text address. Offence groups use official broad codes 03–16; omit them to return all published local groups. This is NOT a street-level crime heatmap or a property safety assessment. CSO station data applies to the entire Garda sub-district polygon: incidents have no published coordinates and may have happened anywhere within it. Never infer a hotspot near the address, spread incidents evenly across the polygon, combine categories into a score, or label the property/area safe or unsafe. Homicide (01) and sexual offences (02) are not published at this local resolution and are explicitly reported as unchecked. Resident-based rates are weak in city centres, airports, retail and nightlife areas with large non-resident populations; enforcement activity also affects some categories. Recorded incidents use PULSE report dates, can be revised, and are not a measure of all crime experienced. Fraud has a 2023 break and a narrower public-reported series from 2024.
Compass MCP tools 18
compass_search_propertiesSearch Compass listings by location (city, ZIP, neighborhood) and optional filters. Resolves free-text via slugification into Compass's URL routing, then fetches the SSR search-results page and extracts the embedded listings array. Compass server-renders ~41 listings into that page (its `num`), and `total_items` reports the full market count. PAGINATION (issue #87): Compass no longer paginates the SSR search via any URL — `/page-N/`, `?page=N`, and `?start=N` all canonicalize back to page 1 and return the identical listings, so only the first SSR page (~41 listings) is reachable through this primitive. `offset` is honored WITHIN that page, and `next_offset` is emitted only when more listings remain within it — it is never a false cursor that re-fetches page 1. TO REACH BEYOND THE FIRST PAGE, narrow with `price_min` / `price_max` / `beds_min`/`beds_max` to bucket the result set into <~41-listing bands (price-banding), then search each band. Returns each matching listing's address, price, beds/baths, sqft, lat/lng, the Compass homedetails URL (`_lid/` form, content-addressed by `listing_id_sha`), and the stable `_pid/` URL via `property_url` and the surfaced `pid` field. The per-listing `primary_photo_url` / `primary_thumbnail_url` are omitted in the default `compact` view (they are Compass CDN URLs a model cannot see); pass `view: "full"` to get them, or `compass_get_property_photos` for the whole gallery. USE `pid`/`_pid/` FOR LONG-LIVED REFERENCES (trackers, sheets, bookmarks) — sha-based `_lid/` URLs change when a property is delisted and relisted. Use the sha-based URL to fetch the current listing record. Read-only; safe to call repeatedly.compass_get_propertyFetch a property's full Compass record. Pass either `url` (a full Compass homedetails URL or path from a compass_search_properties result) or `listing_id_sha` alone — when only the sha is supplied, the tool fetches /listing/<sha>/view, which redirects to the canonical /homedetails/<slug>/<sha>_lid/ page. Returns address, neighborhood, beds/baths, sqft, lot size (`lot_size_sqft` plus the derived `lot_size_acres` = round(sqft / 43560, 2), null — never 0 — for condos / missing lots), price + price-per-sqft, monthly charges, MLS status, amenities, schools, parcel number, and the canonical Compass URL. Also returns `extracted_features` (lake_front, hot_tub, basement, furnished, dock, community) keyword-parsed from the description. DESCRIPTION HANDLING: The raw `description` (Compass marketing copy) is omitted by default — pass `include_description: true` to keep it. `extracted_features` is always populated and usually sufficient. URL FORMS: Compass exposes two URL shapes for a listing. `_lid/` (content-addressed by `listing_id_sha`) — what this tool fetches and what `url` returns — is the form to use for reading the current listing record. `_pid/` (opaque short ID, in `property_url` and the surfaced `pid` field) is **stable across re-listings** and is the right choice for any long-lived reference (trackers, sheets, bookmarks); sha-based URLs go stale when a property is delisted and relisted. Read-only; safe to call repeatedly.compass_get_saved_homesNot yet supported — Compass renders /overview/favorites via an auth-scoped GraphQL we have not yet identified. Throws a clear error explaining the limitation.compass_get_saved_searchesNot yet supported — Compass renders saved searches via an auth-scoped GraphQL we have not yet identified. Throws a clear error explaining the limitation.compass_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.compass_get_price_historyFull listing history for a Compass property — Listed / Sold / Pending / Price Change / Delisted events with date, price, and MLS attribution. Returns three arrays: `events` covers this listing's events, `history` aggregates events from prior listings of the same property, and `events_normalized` merges both into a shared cross-MCP schema (`{date, type, price?, price_change_pct?, source_mls?}` with a fixed type enum: Listed | PriceChange | Pending | Contingent | Sold | Withdrawn | Relisted | Delisted). Pass either `url` (the full Compass homedetails URL or path) or `listing_id_sha` alone — sha-only calls fetch /listing/<sha>/view, which redirects to the homedetails page. Note: most of this data is already returned inline on `compass_get_property` (the events[] / history[] arrays live on the same listing record); call this tool only when you want the merged + normalized timeline. Read-only; safe to call repeatedly.compass_compare_propertiesFetch 2 or more Compass properties and align their facts side-by-side. Each target may supply `url` (a full Compass homedetails URL or path) or `listing_id_sha` alone — sha-only targets fetch /listing/<sha>/view, which redirects to the homedetails page. Returns the full per-property record per row (with `extracted_features` populated). 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`), `retryable` and `error`, and the envelope reports `count` / `ok` / `errored`. Calls are concurrent, and the whole call is bounded by an overall deadline: any row still unsettled when it is reached comes back as `{ status: "pending", retryable: true, error }` with a top-level `pending` count — re-run just those targets. The raw `description` is omitted from each row by default — pass `include_description: true` to keep it. The redundant `summary` table is also opt-in via `include_summary: true` — by default only `results[]` is returned, which already carries every fact.compass_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.compass_get_property_photosThe full photo gallery for a Compass listing — every image in listing.media[]. Each entry returns the original CDN URL plus a thumbnail URL and pixel dimensions. Pass either `url` (the full Compass homedetails URL or path) or `listing_id_sha` alone — sha-only calls fetch /listing/<sha>/view, which redirects to the homedetails page. By default only photos (category 0) are returned; set `include_all_categories: true` to also include floorplans and other media. Returns `{ listing_id_sha, count, photos }`. Read-only; safe to call repeatedly.compass_healthcheckRound-trips a small public www.compass.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.compass.com-side problem'. Read-only, no auth required. Call this when a real tool fails and you want to know which hop broke.compass_get_by_addressResolve a free-text street address to a Compass listing's canonical URL and identifiers in one call. Walks three rungs: first the structured typeahead `POST /api/v3/omnisuggest/autocomplete` (the primary rung — Compass's address-suggest API, which routes around the AWS WAF that 403s the SSR free-text path, issues #78/#79), then `/homes-for-sale/?q=<address>` (the free-text rung) and — when those return no verified match — a slug-based search at `/homes-for-sale/<city-state-or-zip>/` (the search-fallback rung, issue #71). Each candidate is verified against the query (case + street-type abbreviation normalization, then whole-token equality, issue #45) before being accepted. Returns `{ url, listing_id_sha, pid, address, resolved, matched_via }` where `matched_via` is `"typeahead"`, `"freetext"`, or `"search_fallback"` so callers can see which rung found the match. When no rung matches, returns `{ resolved: false, error: "no listing matched" }` rather than leaking a wrong URL. When the lookup was blocked by a sign-in / AWS WAF challenge instead, it returns `{ resolved: false, status: "auth_required", error, hint }` — NOT a miss: sign in to compass.com in the browser and retry. The `url` is the stable `_pid/` form when Compass provides a `navigationPageLink` (preferred for trackers/bookmarks — sha URLs go stale on relisting), falling back to the `_lid/` form otherwise. Read-only; safe to call repeatedly.compass_bulk_getFetch up to 200 Compass listings in a single call. Returns one structured row per input target (no side-by-side summary table — use `compass_compare_properties` for that). Each row is either `{ listing_id_sha, url, status: "ok", property }` on success or `{ listing_id_sha, url, status, error_kind, retryable, error }` on failure (`status` = `error_kind`) — one bad target never fails the whole call. `retryable: true` (a bridge `timeout` after one retry, an unreachable `bridge_down`, issue #73) is NOT a missing listing, so retry it (a cold bridge usually succeeds on the second call) rather than concluding Compass has no record; `protocol` / `other` are real misses. Targets accept the same `url` / `listing_id_sha` shape as `compass_get_property`. Calls fan out concurrently. The whole call is bounded by an overall deadline: a slow or hung row never wedges it — any row still unsettled when the deadline is reached comes back as `{ status: "pending", retryable: true, error }` alongside a top-level `pending` count, so re-run just those targets. The envelope also reports `count` / `ok` / `errored`. `extracted_features` is populated per row. The raw `description` is omitted by default — pass `include_description: true` to keep it.- +6 more on the listing page
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.
Gaff Check
{
"mcpServers": {
"gaff-check": {
"command": "npx",
"args": [
"-y",
"gaff-check"
]
}
}
}
Compass MCP
{
"mcpServers": {
"compass-mcp": {
"command": "npx",
"args": [
"-y",
"compass-mcp"
]
}
}
}
Frequently asked questions
Gaff Check is categorized under Real Estate and uses a local stdio subprocess. Compass MCP belongs to Real Estate and uses a local stdio subprocess. Pick Gaff Check for real estate work and Compass MCP 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.
Gaff Check has no declared pricing — check the project's own site. Compass MCP 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 gaff-check and compass-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Gaff Check has a quality signal of 61/100 (Good) with 1 views, 0 installs and 8 GitHub stars. Compass MCP has 61/100 (Good) with 1 views, 0 installs and 0 GitHub stars.