Fetch up to 200 OneHome listings in a single call. Returns one structured row per input id (no side-by-side summary table — use onehome_compare_properties for that). Each row is either { listing_id, status: "ok", property } on success or { listing_id, status, error_kind, retryable, error } on failure (status = error_kind: timeout / bridge_down / pending are retryable, protocol / other are real misses) — one bad id never fails the whole call. Calls fan out concurrently against ListingById, capped at 6 in flight to avoid swamping the bridge; transient timeouts are retried once per row before being captured as an error. The whole call is bounded by an overall deadline: any row still unsettled comes back status: "pending" with a top-level pending count — re-run just those ids. The envelope reports count / ok / errored. extracted_features is populated per row automatically. The raw description (PublicRemarks) is omitted by default — pass include_description: true to keep it. group_id defaults to the magic-link session context.

Solve 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.

Local-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.

Fetch 2 or more OneHome listings and align their facts side-by-side. Each target may supply listing_id (preferred) or url (a portal URL). Returns the full per-property record (with extracted_features populated) per row. Per-target errors are captured per-row — one bad target will not fail the whole call. Calls are concurrent. The raw description is omitted from each row by default (include_description: true to keep it). The redundant summary table is also opt-in via include_summary: true — by default only rows[] is returned, which already carries every fact.

Resolve a free-text street address (with optional city/state/zip) to a OneHome listing's canonical portal URL and id in one call. Walks a 2-rung ladder: (1) ListingSuggestionsSearch against the magic-link saved-search scope; (2) when that misses, search-fallback — page-walks the broader saved-search (or raw listings(groupId)) pool bounded by the same groupId and fuzzy-matches input address tokens. Returns { url, listing_id, address, resolved, matched_via } where matched_via: "suggestions" | "search_fallback" reports which rung produced the hit. When no listing matches, returns { resolved: false, error: "no listing found" } rather than throwing. Read-only; safe to call repeatedly.

List the OneHome groups your agent has shared with you. Share member e-mails and the agent's e-mail/phones are omitted unless include_contacts: true. For full agent / registered users, returns the GraphQL user.groups list. For magic-link consumer-share sessions (a single shared group), synthesizes a one-entry list from the checkToken session context.

Fetch full details for a single OneHome listing by id or portal URL. Returns address, list / close / previous price, $/sqft, beds/baths/sqft, lot size (raw lot_size {area, units} plus the derived lot_size_acres — null, never 0, for condos / lotless listings), year built, lat/lng, status, HOA fee, annual tax, virtual-tour URL, the primary photo, and an extracted_features block (lake_front, hot_tub, basement, furnished, dock, community) keyword-parsed from the description. The raw description (PublicRemarks) is omitted by default — pass include_description: true to keep it; in most cases the extracted features cover what callers need. OneHome scopes every listing to a group/market — group_id defaults to the magic-link session context; pass it explicitly only if you need to query a different group.

Fetch the full media gallery for a OneHome listing. Returns one entry per image with Thumbnail / Medium / Large CDN URLs, dimensions, the listing-room description (LongDescription), and display order. Pass either listing_id or a portal URL.

Fetch the agent-curated saved search by its id (UUID). Returns the search's name, filter criteria (filters[]), polygon, listing count, and the full list of OSK listing ids that compose the consumer share (listing_ids). Pass include_listing_ids: false to suppress the listing-id array if you only need the metadata. This is the canonical consumer-readable endpoint; the by-groupId variant is agent-only. saved_search_id defaults to the MCP's session context when omitted.

Combo tool: the "show me my saved homes" flow in a single round trip. Internally runs GetSavedSearchBySearchId to fetch the saved search (name, filters, polygon, listingIds) and then GetSavedListings to inflate those listingIds into full property records — the same two-call sequence as calling onehome_get_saved_search followed by onehome_search_properties(saved_search_id=...), but exposed as one tool so the magic-link-to-listings consumer flow is a single MCP call. Returns { saved_search, listings, count, page_info }. Both saved_search_id and group_id default to the magic-link session context. Sort defaults to property.MajorChangeTimestamp DESC (Newest). Listings are returned via the GraphQL listing-card projection (buildGetSavedListings), which does NOT include PublicRemarks — so there is no raw description to opt back into here. Use onehome_get_property(listing_id) per row when you need the full description for a specific listing. view: "brief" answers one line per listing instead: address · price — date of its last change — status, change (e.g. a new listing or a price decrease), inside the untrusted-data envelope as data: string[], with -- none for an empty saved search and -- N of M shown when the page holds fewer listings than the search.

Fetch the Local-Logic school data for a coordinate — separate primary and high-school lists, each entry with name, attributes (types/grades/programs/levels), and proximity (walking distance + straight-line distance). Returns an error field with HTTP details if the consumer session does not have access (the schools endpoint is sometimes agent-only). lat/lng usually come from onehome_get_property (latitude / longitude).

Returns one entry per registered session — its session_id, auth_mode, token expiry, and session scope (group_id / saved_search_id / agent_id / contact_id / mls_id) the MCP bootstrapped from each checkToken exchange. active_session_id flags which session answers by default; per-listing routing uses the active session when its mls_id matches the listing's ~MLS suffix, else the one session that matches (several matches error — pick one with onehome_set_active_session). Tools default unspecified group_id / saved_search_id arguments from the active session's context, so this is the easiest way to see what they'll default to. Single-session use (the common case) returns a one-entry sessions[].

Returns the OneHome user profile + the consumer-share groups attached. Share member e-mails and the agent's e-mail/phones are omitted unless include_contacts: true. For full agent / registered users, queries the GraphQL user endpoint. For magic-link consumer-share sessions (where user { } is access-denied), falls back to the data captured during the checkToken exchange — email, contact id, group/savedSearch ids, and the agent who shared with you.

Local-Logic location scores for a coordinate — pedestrian / car / cycling / transit friendliness, plus proximity summaries for groceries, restaurants, parks, primary + high schools. Each score is a { value, text } pair (value 0-5, text a one-line description). Returns an error field with HTTP details if the upstream rejected the request.

Power-user escape hatch — send a raw GraphQL document with variables. Returns the whole { data, errors, status, url } envelope, unprojected, so you can read upstream schema errors directly. Note the default: view is compact, which strips image/avatar URLs out of data (every envelope key and every non-media field is kept). Pass view: 'full' when you need the envelope byte for byte — worth doing if you are here because a payload is not what you expected, so a missing field is never this server's doing. Operation names live in the portal bundle; common ones include GetOneHomeUser, GetListings, GetPins, ListingById, MediaListingById, GetSavedSearches, ListingSuggestionsSearch. (LocalLogic schools/walk-score are REST endpoints, not GraphQL operations — use onehome_get_schools / onehome_get_walk_score.) Pass query (the full document body), an operation_name matching the document, and any variables as JSON. Read-only: documents containing a mutation or subscription operation — or that cannot be parsed as a read-only query document — are refused.

Round-trip a minimal authenticated query through the configured transport. Picks GetSavedSearchBySearchId for magic-link consumer-shares (works for them) or GetOneHomeUser for agent/registered sessions. Returns the auth mode, token expiry, fetchproxy bridge role (when applicable), elapsed time, and any error detail. Run this first when a tool fails — it isolates "is auth wired up?" from "is the API itself misbehaving?".

Resolve up to 100 structured addresses to OneHome canonical portal URLs + listing OSK ids in one call. Each input is a {address, city?, state?, zip?} object. Output preserves input order; one row per input, either {resolved: true, url, listing_id, address} or {resolved: false, error, query}; a row that failed (rather than genuinely missed) also carries status = error_kind and retryable — timeout / bridge_down / pending mean retry it, not "no listing". The whole call is bounded by an overall deadline; unsettled rows come back status: "pending" with a top-level pending count. Walks the exact same 2-rung ladder as onehome_get_by_address via the shared helper (rung 1: ListingSuggestionsSearch against the magic-link saved-search scope; rung 2: search-fallback page-walking the broader saved-search / raw-listings pool bounded by groupId) — bulk and single cannot diverge. Each row surfaces matched_via: "suggestions" | "search_fallback" so callers see which rung produced the hit. Concurrent fan-out capped at 6 in flight to avoid swamping the upstream. Per-row errors captured — one bad address never fails the whole batch. group_id defaults to the magic-link session context. Read-only; safe to call repeatedly.

Fetch listings inside a OneHome consumer-share. Two modes:

• With saved_search_id: fetch the agent-curated collection (the standard 'Homes at ' view). The MCP first resolves the saved search's listingIds and then inflates them via listingsBySavedSearchId — this is the only mode that works for non-agent consumer accounts.

• With just group_id and no saved_search_id: try the raw listings(groupId, browseParameter) endpoint. If page 0 comes back empty with no reported results (the access-restricted shape consumer-shares hit) AND the session context has a savedSearchId for that same group, the tool falls back to the saved-search path and marks the response fell_back_to_saved_search: true. If there's no fallback target it raises a clear error rather than silently returning empty. An empty later page (paging past the end) is returned as an empty page, never swapped for the saved-search collection.

Both args default from the MCP's bootstrapped session context (the magic-link checkToken response) when neither is passed explicitly. Sort is MajorChangeTimestamp DESC ('Newest') unless overridden. include_dislikes: false by default — flip it on to include listings you've thumbs-downed in OneHome.

Listings here are returned via the GraphQL listing-card projection, which does NOT include PublicRemarks — so there is no description field on search results and no include_description flag to opt into one. Each listing carries the structured extracted_features object instead. Use onehome_get_property(listing_id) per row when you need the full description for a specific listing.

Cross-feed suggestion search by address, MLS number, or partial query. Bypasses the group/saved-search structure and hits the global suggestion endpoint — useful for "find an address" or "look up by MLS number". Returns id, address parts, beds/baths, list price, thumbnail per match. Inflate any result with onehome_get_property. Optional group_id scopes suggestions to one OneHome market.

Force a specific registered session to be the active one. Useful when MLS-suffix routing picks the wrong session (e.g. two shares in the same MLS, a free-text search across multiple MLSes, or a listing without a ~MLS suffix). Pass a session_id previously returned by onehome_set_auth or surfaced in onehome_get_session_context. The active session answers any request without a ~MLS-suffixed listing id AND any ~MLS request whose MLS matches its own; a ~MLS id matching several other sessions errors until you pick one here.

Provide a magic-link URL, a raw JWT bearer, or an email-token to ADD another authenticated session to the MCP — useful when a buyer holds shares across multiple agents/MLSes (one magic link per share). The MCP detects the input shape (URL → extract ?token=; 3-segment JWT → use directly; otherwise → treat as email-token and exchange via /api/authentication/checkToken), registers a new direct-bearer transport, and marks it active. Previously-registered sessions stay registered — switch back with onehome_set_active_session(session_id), or let MLS-suffix routing (~CANOPY, ~HCAOR, …) pick automatically per listing. The response includes the assigned session_id, the new active_session_id, the auth_mode/status, the session_context the checkToken response yielded, and a bearer_fingerprint of the resolved JWT (first 8 + … + last 4 chars) — never the full bearer. SECURITY: the input itself sits in your chat history; treat magic links as short-lived credentials.