Homes MCP vs Firecrawl MCP Server
A side-by-side look at the Homes MCP and Firecrawl MCP Server 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 Firecrawl MCP Server for search & data extraction 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 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.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Real Estate | Search & Data Extraction |
| Quality signal | 63/100 · Good | 90/100 · Excellent |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | other | API key required |
| Pricing | Free | Freemium |
| Required env vars | None listed | FIRECRAWL_API_KEYHTTP_STREAMABLE_SERVER |
| Verified owner | Community listing | Verified |
| GitHub stars | 0 | 7,673 |
| Directory activity | 2 views 0 installs 0 upvotes | 14 views 0 installs 0 upvotes |
| Tools | 21 | 25 |
| Full listing | View Homes MCP | View Firecrawl MCP Server |
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
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
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"
]
}
}
}
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"
}
}
}
}
Frequently asked questions
Homes MCP is categorized under Real Estate and uses a local stdio subprocess. Firecrawl MCP Server belongs to Search & Data Extraction and uses a local stdio subprocess. Pick Homes MCP for real estate work and Firecrawl MCP Server for search & data extraction.
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. Firecrawl MCP Server is listed as freemium — a free tier with paid plans. Auth: api key required. 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 firecrawl-firecrawl-mcp-server 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. Firecrawl MCP Server has 90/100 (Excellent) with 14 views, 0 installs and 7,673 GitHub stars.