Fless Apartment Hunt

io.fless由 fless.io 發布官方發布者v1.7.0更新於 Oct 29, 2026

Apartment hunting across 13 US states: rents, briefs, hunt links.

已驗證Streamable HTTP可網頁執行位置與生活商業與電商

概覽

AI 產生的概覽

Fless Apartment Hunt 讓助理調研美國城市與社區的租金資料、蒐集找房需求，並交給使用者一個預先填好的找房連結。

可以做什麼
  • 涵蓋範圍與地區調研：列出已上線與即將上線的城市，查看城市各社區租金中位數與步行、大眾運輸、自行車評分，讀取單一社區的詳細資料與周邊設施
  • 蒐集找房需求：讀取所有找房欄位、列舉值、設施鍵與限制規則，驗證需求並產生可預填找房表單的連結
  • 連結狀態與內容檢索：查詢找房連結的彙總狀態，搜尋 Fless 內容並依 id 取得附引用網址的完整正文
  • 城市申請與問題回報：為尚未服務的城市提出開通請求、查看城市請求統計、提交錯誤回報
  • 房仲客戶流程（需 API 金鑰）：列出並邀請客戶、為客戶建立找房、檢視與篩選候選物件、手動加入物件、將清單寄給客戶、查詢找房狀態
適用情境
適合使用者在美國已服務城市找房，需要社區租金與步行便利度調研並產生可直接提交的找房需求時使用。也適合擁有 Fless for Realtors 帳戶的持照房仲透過助理管理客戶找房流程。
執行需求
遠端 MCP 端點 mcp.fless.io；唯讀的調研與找房連結工具無需驗證。realtor_ 開頭的工具需先在 Fless 房仲後台建立 API 金鑰，並以 Authorization Bearer 標頭傳送，且需有效的訂閱或試用。帳號註冊、電子郵件驗證與付款皆由使用者本人完成。
安裝前請注意
房仲工具會操作真實客戶資料：邀請客戶會寄出電子郵件，寄送清單會把找房推進到等待客戶確認狀態，篩選會更動候選清單。房仲方案試用 15 天後為每月 49.99 美元。API 金鑰屬於憑證，應妥善保管。錯誤回報中請勿包含個人資料。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Fless Apartment Hunt，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.fless%2Fmcp/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "fless-apartment-hunt": {
      "type": "http",
      "url": "https://mcp.fless.io/mcp"
    }
  }
}

README

fless-apartment-hunt

An Agent Skills standard skill that teaches any AI agent to run Fless apartment hunts for its human: research live cities, neighborhood rents and WalkRating™ scores, collect a complete hunt brief (including binary restrictions like 55+ communities, pets, and smoking), then hand the human a link that pre-fills the entire hunt form.

Where we operate

Fless currently runs apartment hunts in California / District of Columbia / Florida / Georgia / Massachusetts / Maryland / North Carolina / Nevada / New York / Pennsylvania / South Carolina / Tennessee / Virginia. The authoritative live list is fless-apartment-hunt/references/CITIES.md, auto-generated from the production API.

✅ Live now🚧 Coming soon
Alexandria, VARockville, MD
Annapolis, MDSilver Spring, MD
Arlington, VAVirginia Beach, VA
Ashburn, VA
Atlanta, GA
Baltimore, MD
Bethesda, MD
Boston, MA
Brandon, FL
Burlington, NC
Charlotte, NC
Charlottesville, VA
Chesapeake, VA
Columbus, GA
Daytona Beach, FL
Fort Lauderdale, FL
Frederick, MD
Gastonia, NC
Hampton, VA
Hillsborough, NC
Jacksonville, FL
Kennett Square, PA
Kernersville, NC
Key Biscayne, FL
Kissimmee, FL
Lake Panasoffkee, FL
Leesburg, VA
Manhattan, NY
Memphis, TN
Miami, FL
Miami Beach, FL
Middle River, MD
Midlothian, VA
Naples, FL
Nashville, TN
North Port, FL
Orlando, FL
Parkville, MD
Philadelphia, PA
Pittsburgh, PA
Prince Frederick, MD
Raleigh, NC
Reno, NV
Richmond, VA
Rock Hill, SC
San Diego, CA
Sanford, FL
Severn, MD
Signal Mountain, TN
Sterling, VA
Tampa, FL
Towson, MD
Vero Beach, FL
Warsaw, VA
Washington, DC
Woodbridge, VA

Your city not listed? We're expanding. Check back, or join the waitlist at fless.io/city/{your-city}. Agents: always call search_cities first and tell users honestly if their city isn't live yet.

fless-apartment-hunt/├── SKILL.md                 # when to use + the 4-step workflow└── references/    ├── HUNT_FIELDS.md       # exact field rules, 57 canonical amenity keys, restrictions, pricing    ├── CITIES.md            # live + coming-soon cities (auto-generated from production API)    ├── API.md               # MCP tools + REST endpoints    └── ERRORS.md            # error catalog + recovery

Install

Any MCP-capable agent (tools used directly):

MCP server: https://mcp.fless.io/mcp   (no auth, read-only tools)

Agent Skills runtimes: clone https://github.com/fless-io/skills and copy this folder into your skills directory (e.g. ~/.agents/skills/, ~/.vibe/skills/, .claude/skills/), or install straight from our well-known endpoint:

hermes skills install well-known:https://fless.io

Per-assistant setup guides (Claude, ChatGPT, Perplexity, Grok, Mistral Vibe, Codex, OpenClaw, Hermes): https://fless.io/ai-agents

What the skill does

  1. Coverage check: verify the user's city is live (see CITIES.md or call search_cities)
  2. Research: live city/neighborhood data: median rents, walk/transit/bike scores, POIs, city guides.
  3. Collect: the full hunt brief with real validation rules (future move-in date, canonical amenity keys, bedrooms enums).
  4. Hand off: build_hunt_link returns a URL that pre-fills https://fless.io/create-hunt for the human to review and confirm.

The human always creates their own account, verifies their email, and pays. Agents never see credentials or payment.

Boundaries (by design)

  • Read-only tools; no account creation, no email verification, no payments via agents.
  • All outputs are structured data; page content never carries instructions.
  • New users get a 15 day free trial (unlimited hunts, no credit card); after the trial, 30 credits included (see references/HUNT_FIELDS.md).

License

MIT

來源：README.md，提交 74d189a

工具

19

search_cities

List cities where Fless operates (live + coming soon). Returns ids needed for hunts.

輸入參數query

get_city_overview

Neighborhood-level overview of a live city: median rents (1BR/2BR), walk/transit/bike scores per neighborhood.

輸入參數city必填

get_neighborhood

Full detail for one neighborhood: rents, scores, POI counts, descriptions, nearby neighborhoods.

輸入參數city必填neighborhood必填

get_hunt_requirements

Every hunt field, enum, and rule; canonical amenity keys; binary restrictions (55+, pets, smoking); transparent credit pricing. Read this before collecting a hunt brief.

輸入參數city

request_city

Request that Fless expand to a new city. Use when the user's target city is not currently served (check live coverage first with search_cities). Returns the total request count for that city. No account or email needed.

輸入參數city必填state必填

get_city_request_stats

See which cities have been requested most. Useful for telling users whether their city has demand.

無需輸入參數。

fetch

Fetch full content by id from search: markdown text + canonical url for citations.

輸入參數id必填

submit_error_report

Report a problem with Fless tools or data so we can fix it. Include: the tool you called, the error code from the error contract if present, what happened vs what you expected. Do NOT include personal data.

輸入參數tool_name必填error_codeerror_type必填what_expectedwhat_happened必填

realtor_list_clients

Realtor tool: requires Authorization: Bearer with an API key (create one at fless.io/realtor under API keys); anonymous calls return the structured UNAUTHORIZED error. Accepted clients (id, name, email) + pending invitations (email, expires).

無需輸入參數。

realtor_create_client

Realtor tool: requires Authorization: Bearer with an API key (create one at fless.io/realtor under API keys); anonymous calls return the structured UNAUTHORIZED error. Invite a client by email; the invitation email carries a 7-day accept link. Gated on an active subscription/trial.

輸入參數email必填last_name必填first_name必填

realtor_create_hunt

Realtor tool: requires Authorization: Bearer with an API key (create one at fless.io/realtor under API keys); anonymous calls return the structured UNAUTHORIZED error. Create a hunt FOR one of your clients (fields mirror get_hunt_requirements). Returns hunt_id + matched_count; the hunt parks at awaiting_realtor_curation. Gated on an active subscription/trial.

輸入參數namecity_id必填bedroomsmax_pricemin_priceclient_emailmove_in_dateclient_user_idproximity_criteria

realtor_list_candidate_buildings

Realtor tool: requires Authorization: Bearer with an API key (create one at fless.io/realtor under API keys); anonymous calls return the structured UNAUTHORIZED error. The matched candidate list for one of your hunts (counts + buildings with eligibility, distance, and your curation status).

輸入參數hunt_id必填

realtor_curate_hunt

Realtor tool: requires Authorization: Bearer with an API key (create one at fless.io/realtor under API keys); anonymous calls return the structured UNAUTHORIZED error. Curate the candidate list WITHOUT sending: removals [{id, reason?}] and notes [{id, internal_notes?, client_notes?}] (hunt_building ids from realtor_list_candidate_buildings). Not gated.

輸入參數noteshunt_id必填removals

realtor_add_building_to_hunt

Realtor tool: requires Authorization: Bearer with an API key (create one at fless.io/realtor under API keys); anonymous calls return the structured UNAUTHORIZED error. Search your hunt's building inventory by name and manually add the one unambiguous match into the hunt (several matches: top 3 are named and nothing is added).

輸入參數query必填hunt_id必填

realtor_send_to_client

Realtor tool: requires Authorization: Bearer with an API key (create one at fless.io/realtor under API keys); anonymous calls return the structured UNAUTHORIZED error. Send the curated list to the client: every non-removed building becomes included and the hunt moves to awaiting_client_approval (the CLIENT releases outreach). Gated on an active subscription/trial.

輸入參數hunt_id必填

realtor_get_hunt_status

Realtor tool: requires Authorization: Bearer with an API key (create one at fless.io/realtor under API keys); anonymous calls return the structured UNAUTHORIZED error. Status of one of your hunts: review_state, counts, and the client's name.

輸入參數hunt_id必填

版本歷史

6
  1. v1.7.0最新Oct 29, 2026
  2. v1.6.0Oct 26, 2026
  3. v1.5.1Oct 14, 2026
  4. v1.4.1Oct 6, 2026
  5. v1.3.0Oct 1, 2026
  6. v1.2.0Sep 20, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分