Firecrawl MCP Server vs Onehome MCP
A side-by-side look at the Firecrawl MCP Server 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 Firecrawl MCP Server for search & data extraction 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 Firecrawl MCP Server when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
FIRECRAWL_API_KEY, HTTP_STREAMABLE_SERVER. - You want tools like
firecrawl_scrape, firecrawl_map, firecrawl_search.
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 | Search & Data Extraction | Real Estate |
| Quality signal | 90/100 · Excellent | 63/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | API key required | Not declared |
| Pricing | Freemium | Not declared |
| Required env vars | FIRECRAWL_API_KEYHTTP_STREAMABLE_SERVER | ONEHOME_TOKENONEHOME_MAGIC_LINK |
| Verified owner | Verified | Community listing |
| GitHub stars | 7,669 | 1 |
| Directory activity | 13 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 25 | 21 |
| Full listing | View Firecrawl MCP Server | View Onehome MCP |
Tools & capabilities
Firecrawl MCP Server tools 25
firecrawl_scrapeRetrieve and extract content from one supplied URL through Firecrawl. Use this when the request identifies a page and needs its content or defined fields. It can return markdown, HTML, links, screenshots, branding data, a targeted answer, or JSON matching a supplied schema; JSON is useful when the requested result has defined fields, while markdown preserves readable page content. This tool operates on a known page. For a set of pages use `firecrawl_crawl`, and to discover page URLs use `firecrawl_map` or `firecrawl_search`. Options include JavaScript render delay, cache age, main-content filtering, PII redaction, and lockdown cache-only retrieval. Browser actions may change the live page when interactive actions are enabled. Firecrawl may reuse recently indexed content instead of refetching the page, and the reuse window varies by domain. Set `maxAge: 0` to force a live fetch, or a smaller `maxAge` to bound how stale reused content may be. A successful response does not by itself confirm that the state it describes is still current. Returns the selected content formats and page metadata.firecrawl_mapEnumerate URLs indexed under one website through Firecrawl without fetching each page's content. Use this when the request asks for a site's URL inventory, when several relevant pages must be located, or when the desired page URL is unknown. An optional `search` term narrows the URL list, while sitemap, subdomain, query-parameter, and result-limit options control coverage. Returns matching URLs rather than page bodies. Retrieve one page with `firecrawl_scrape`; collect content across multiple pages with `firecrawl_crawl`.firecrawl_searchSearch web, news, or image sources and return ranked results. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. `includeDomains` and `excludeDomains` are mutually exclusive hostname filters; categories limit results to GitHub, research, PDF, or developer sources. For a programming question, add `categories: ["developer"]`. It searches an index of GitHub issues, merged pull requests, repository READMEs, and curated documentation sites, and returns the hits in `data.developer` beside the web results. `categories: ["research"]` restricts these web results to research-affiliated websites and returns page snippets. The `firecrawl_research_*` tools are a separate surface that searches paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature. `scrapeOptions` can attach extracted page content; pages fetched this way use a fixed reuse window and ignore `maxAge`, so use `firecrawl_scrape` when a live fetch is required. Returns source-type result groups and usage metadata. Authenticated responses can include an `id` for optional search feedback.firecrawl_crawlStart a multi-page crawl at a website URL, poll it to a terminal state, and return the final status and collected data. Scope can be bounded with include/exclude paths, depth, page limit, subdomain/external-link controls, sitemap handling, delay, and scrape options. Crawl results can be large; use conservative limits when full-site coverage is unnecessary. Webhooks and interactive scrape actions are unavailable in safe mode. Returns the crawl ID, status, and page data.firecrawl_check_crawl_statusRetrieve the current status, progress, and available results for an existing crawl ID. This only reads Firecrawl job state and does not start or modify the crawl.firecrawl_extractDeprecated compatibility entry point. Use firecrawl_scrape once per known URL with formats: ["json"] and jsonOptions containing the prompt and schema. Use firecrawl_search or firecrawl_agent before Scrape when URLs are not known.firecrawl_agentStart an asynchronous web research job from a prompt, optional seed URLs, and an optional JSON schema. Use this for a requested synthesis across multiple sources when the task can wait for asynchronous completion. The agent can search, navigate, read pages, and assemble a structured result. This call returns only a job ID, not the research result. Read the job with `firecrawl_agent_status` until it reaches `completed` or `failed`; research commonly takes several minutes. If the job cannot finish within the task's available time, `firecrawl_search` and `firecrawl_scrape` can gather evidence synchronously.firecrawl_agent_statusRetrieve progress or final results for a `firecrawl_agent` job ID. A `processing` response is non-terminal and does not contain the final research result. Check again after 15–30 seconds until the status is `completed` or `failed`; complex jobs can take several minutes. If the job cannot finish within the task's available time, use `firecrawl_search` and `firecrawl_scrape` to complete the requested output. Returns job status, progress information, and result data when completed.firecrawl_interactOpen or reuse a live browser session to navigate a page, click controls, fill fields, or run browser code. Provide either `url` or `scrapeId`, and either a natural-language `prompt` or executable `code`; code can run as Bash, Python, or Node with a bounded timeout. This acts on the live site, so actions such as form submission can create persistent external side effects. Returns execution output, stdout/stderr, exit status, and session viewing URLs.firecrawl_interact_stopStop the live interact session associated with a `scrapeId` and release its resources. Returns a success confirmation.firecrawl_parseParse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with `pdfOptions.maxPages`. Local MCP reads `filePath` from the server filesystem. Hosted MCP uses two calls: first provide `filePath` to receive upload instructions, upload locally, then call again with the returned `uploadRef`; do not send both fields together. Remote web URLs belong in `firecrawl_scrape`. Set `redactPII` to request redaction of personally identifiable information in the returned content. `zeroDataRetention` requires an eligible authenticated account; omit it for anonymous keyless use. Returns upload instructions for hosted phase one or parsed document content for the final call.firecrawl_monitor_createCreate a recurring scrape, crawl, or search monitor that compares each check with its retained predecessor. The simple form accepts `page`/`pages` or `queries` plus a plain-language `goal`; the advanced `body` form controls targets, schedule, change-tracking formats, judging, retention, webhook, and notifications. In the simple form, a `goal` is required. If `queries` contains one or more non-empty values and is supplied with `page`/`pages`, `queries` create the search target and page targets are ignored. A monitor schedules future network checks and can send configured email or webhook notifications. Returns the created monitor.- +13 more on the listing page
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.
Firecrawl MCP Server
{
"mcpServers": {
"firecrawl-firecrawl-mcp-server": {
"command": "npx",
"args": [
"-y",
"firecrawl-mcp"
],
"env": {
"FIRECRAWL_API_KEY": "YOUR_FIRECRAWL_API_KEY_HERE",
"HTTP_STREAMABLE_SERVER": "YOUR_HTTP_STREAMABLE_SERVER_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
Firecrawl MCP Server is categorized under Search & Data Extraction and uses a local stdio subprocess. Onehome MCP belongs to Real Estate and uses a local stdio subprocess. Pick Firecrawl MCP Server for search & data extraction 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.
Firecrawl MCP Server is listed as freemium — a free tier with paid plans. Auth: api key required. 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 firecrawl-firecrawl-mcp-server and onehome-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Firecrawl MCP Server has a quality signal of 90/100 (Excellent) with 13 views, 0 installs and 7,669 GitHub stars. Onehome MCP has 63/100 (Good) with 1 views, 0 installs and 1 GitHub stars.