Propraven vs Onehome MCP
A side-by-side look at the Propraven and Onehome MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Propraven for real estate work as a local process; choose Onehome 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 Propraven when
- You need dedicated capabilities in the Real Estate domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
PROPRAVEN_API_KEY. - You want tools like
parcel_lookup, parcel_search, parcel_compare.
Choose Onehome MCP when
- You need dedicated capabilities in the Real Estate domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
ONEHOME_TOKEN, ONEHOME_MAGIC_LINK. - You want tools like
onehome_get_user, onehome_get_groups, onehome_get_session_context.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Real Estate | Real Estate |
| Quality signal | 60/100 · Good | 63/100 · 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 | PROPRAVEN_API_KEY | ONEHOME_TOKENONEHOME_MAGIC_LINK |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 1 |
| Directory activity | 1 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 8 | 21 |
| Full listing | View Propraven | View Onehome MCP |
Tools & capabilities
Propraven tools 8
parcel_lookupResolve a single US parcel by identifier (canonical state_fips:county_fips:parcel_id, PropRaven UUID, street address, or APN). An ID returns the canonical PropRaven parcel card (GET /api/v1/parcels/{id}): identity, current owner, valuation, geography and source provenance. An address or APN runs the text search and returns up to 5 candidates — re-call with the chosen candidate's `lookup_id` to get the card. Use when the user names one specific property. Do NOT use when ranking multiple parcels (use parcel_compare) or when filtering by criteria (use parcel_search). Example: `parcel_lookup({ query: "37:119:12104406" })` or `parcel_lookup({ query: "2232 Wilmore Dr, Charlotte, NC 28203" })`. Free read — never purchases anything.parcel_searchText search over US parcels (GET /api/v1/search/full): pass `q` as a city, owner name, address fragment or APN, optionally narrowed by `field`, `state` and `city`. Returns `{ results, total, totalCapped, page, pages, hasMore, nextCursor }` (default 50 per page, max 200); each result carries parcel_id, apn, county_fips, state_fips, site_address, city, zip5, owner_name, total_value, latitude, longitude (in search rows `parcel_id` is the PropRaven UUID and `county_fips` is 5-digit), plus `lookup_id`, added by this server — pass it to parcel_lookup / parcel_compare. Page with `cursor` (the previous response's `nextCursor`) rather than `page`; `total` is a floor when `totalCapped` is true. Use when the user wants properties matching a name, place or address fragment. Do NOT use when looking up a single known property (use parcel_lookup) or ranking a known set (use parcel_compare). Free read — never purchases anything.parcel_compareFetch 2–25 parcels side by side so they can be ranked against criteria. For each parcel it reads the free parcel card (GET /api/v1/parcels/{id}: identity, owner, valuation, building, lot) and, unless include_risks=false, the hazard block (GET /api/v1/parcels/{id}/risks), and returns a normalized `summary` plus the raw `card` / `risks`. The calling agent does the per-criterion scoring and final ranking. NEVER buys the paid parcel report or any other paid product. Use when the user has identified candidate properties (often from parcel_search) and wants them ranked. Do NOT use to discover new candidates (use parcel_search) or for a single property (use parcel_lookup + hazard_score). For deed or permit timelines call sales_history / permits_history per parcel. The `criteria` argument is returned verbatim so the agent can pin its scoring to the user's intent.owner_pierceList the parcels titled under an owner-of-record name (GET /api/v1/owners/{name}/portfolio). Returns the matched owner name, a portfolio `summary` (count, total_value, total_acreage, by_state, truncated) and the `properties` list (parcel_id, county_fips, state_fips, address, assessed values, last sale, match_basis, match_confidence). This matches owner-name SPELLINGS — it is NOT a verified corporate, parent-subsidiary or beneficial-ownership link. Use when the user names a person, LLC, trust, or company and wants to see what is titled under that name. Do NOT use when starting from a parcel (use parcel_lookup, which returns owner inline). `ticker` is best-effort: it runs an owner-name search (GET /api/v1/owners/search) for the ticker text and uses the top match, returning the candidates under `resolution` — verify them, or call again with `name`. `state` filters the returned properties client-side (the summary stays portfolio-wide). Free read — never purchases anything.hazard_scoreHazard profile for a parcel (GET /api/v1/parcels/{id}/risks): flood (FEMA zone + SFHA flag), wildfire, seismic, windstorm, air quality and crime blocks, plus withhold_gate / identity_gate provenance. Use when the user asks about a property's risk profile — insurance pricing, underwriting, or due diligence. Do NOT use to compare multiple parcels (use parcel_compare, which includes each parcel's hazards). Every requested key is present: the value, or null when PropRaven does not hold it. Coverage varies by hazard. Free read — never purchases anything (this is not the paid risk-score product).valuation_estimateValue fields for a parcel from its free card (GET /api/v1/parcels/{id}): market_value, avm_value with avm_confidence / avm_method, total / land / improvement assessed value, tax, last sale price and date, price_per_sqft. Numbers are normalized to JSON numbers (null = not held). Use when the user asks for a property's value, market estimate, AVM, or wants to compare assessed vs market. Do NOT use as a substitute for an appraisal — this is a modeled estimate. Historical AVM (as_of) is not supported; the tool returns the current snapshot. Free read — never purchases anything.permits_historyTimeline of building / construction / demolition permits filed against a parcel (GET /api/v1/parcels/{id}/permits). Each permit includes permit_number, permit_type, permit_status, description, work_class, issued_date, completed_date, estimated_cost, contractor_name (where disclosed). Use when the user asks about construction activity, recent renovations, planned work, or wants to detect a property that's actively changing. Do NOT use to find properties WITH recent permits across a market. At most 100 permits are returned (newest first). `permit_count` is the parcel's TRUE count when `permit_count_basis` is "exact"; "capped" means it is the size of the 100-row window (a floor); `truncated: true` means the parcel has more permits than returned. `since` / `types` filter the returned window only (`returned_count` is after filtering). Coverage varies by county. Free read — never purchases anything.sales_historyDeed / transaction timeline for a parcel (GET /api/v1/parcels/{id}/deeds): recorded sales and transfers with recording and sale dates, sale price (where disclosed), grantor (seller), grantee (buyer), deed/document type and book/page. Use when the user asks about a property's transaction history, flip activity, or holding period. Do NOT use to find properties with recent sales market-wide, or to estimate current market value (use valuation_estimate). Note: 13 states do not disclose sale prices on deeds (KS, MS, TX, UT, WY, etc.). `event_count` is the number of events returned. `status` says where they came from: per_deed (deed rows), rollup_events (dated rollup entries), summary_only (no events served, but `known_deed_count` deeds are known — see known_deed_count_basis), or none. UCC liens are NOT available here (they are only in the paid parcel report, which this server never buys). Free read — never purchases anything.
Onehome MCP tools 21
onehome_get_userReturns 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.onehome_get_groupsList 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.onehome_get_session_contextReturns 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[]`.onehome_get_saved_searchFetch 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.onehome_get_saved_search_with_listingsCombo 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.onehome_search_propertiesFetch listings inside a OneHome consumer-share. Two modes: - With `saved_search_id`: fetch the agent-curated collection (the standard 'Homes at <name>' 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.onehome_search_suggestionsCross-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.onehome_get_propertyFetch 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.onehome_get_property_photosFetch 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.onehome_compare_propertiesFetch 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.onehome_bulk_getFetch 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.onehome_get_schoolsFetch 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`).- +9 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.
Propraven
{
"mcpServers": {
"propraven": {
"command": "npx",
"args": [
"-y",
"@propraven/mcp"
],
"env": {
"PROPRAVEN_API_KEY": "YOUR_PROPRAVEN_API_KEY_HERE"
}
}
}
}
Onehome MCP
{
"mcpServers": {
"onehome-mcp": {
"command": "npx",
"args": [
"-y",
"onehome-mcp"
],
"env": {
"ONEHOME_TOKEN": "YOUR_ONEHOME_TOKEN_HERE",
"ONEHOME_MAGIC_LINK": "YOUR_ONEHOME_MAGIC_LINK_HERE"
}
}
}
}
Frequently asked questions
Propraven is categorized under Real Estate and uses a local stdio subprocess. Onehome MCP belongs to Real Estate and uses a local stdio subprocess. Pick Propraven for real estate work and Onehome 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.
Propraven has no declared pricing — check the project's own site. Onehome 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 propraven and onehome-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Propraven has a quality signal of 60/100 (Good) with 1 views, 0 installs and 0 GitHub stars. Onehome MCP has 63/100 (Good) with 1 views, 0 installs and 1 GitHub stars.