原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Fless Apartment Hunt

作者:fless-io版本 1.7.0i★ –i在云端运行
注册名称io.fless/mcp

安装

概览

作者提供的说明(英文原文)

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

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

你需要

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude:

  1. 打开 Settings → Connectors
  2. 点击 Add custom connector
  3. 粘贴下面的地址,然后点击 Add
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Add2https://…3
https://mcp.fless.io/mcp

在终端中运行这条命令

claude mcp add --transport http fless https://mcp.fless.io/mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "fless": {
      "url": "https://mcp.fless.io/mcp"
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "fless": {
      "type": "http",
      "url": "https://mcp.fless.io/mcp"
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

ChatGPT 只能连接互联网上的服务器:

  1. 打开网页版 ChatGPT → Settings → Connectors (Apps)
  2. 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
  3. 粘贴下面的地址,起个名字,然后保存
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Create2https://…3
https://mcp.fless.io/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上,无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

工具名称和描述与服务器在 2026年11月7日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。

  • search_cities

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

  • get_city_overview

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

  • get_neighborhood

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

  • 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.

  • build_hunt_link

    Validate a hunt brief and get a URL that pre-fills the full hunt form for the human. Works with partial briefs (missing_fields lists what to collect).

  • check_hunt_link

    Aggregate status of a hunt link (created/opened/started) — no personal data.

  • 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.

  • get_city_request_stats

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

  • search

    Search Fless content (cities, neighborhoods, hunt guide). Returns citable ids for fetch.

  • fetch

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

  • 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.

  • 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).

  • 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/tria

  • 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; th

  • 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 curati

  • 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_note

  • 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

  • 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_

  • 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.

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 fless.io 验证(注册中心会核实域名所有权)

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • ✓ 通过

    端点有响应

    在 785 毫秒内响应(HTTP 200)

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 19 个工具描述,未发现针对 AI 的隐藏指令

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 18480 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 18480 个服务器的 77% 更新
  • 基础检查结果等于或优于此分类中其他 18480 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Fless Apartment Hunt 安全吗?

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(1.7.0)于12天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, SubA by entendu.

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

作者:formulahendry起步阶段↓ 66/周★ 44014个月前更新

在你的电脑上运行

Remote Desktop Commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

作者:desktop-commander正在增长★ 2113天前更新

在云端运行✓ desktopcommander.app

SubA by entendu.

AI-assisted subtitle localization with project rules, glossaries, review and export.

作者:russellzhengrocks-arch起步阶段今天更新

在云端运行

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

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

问 PopNx