We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, to analyze how the site is used.

You can freely give, refuse or withdraw your consent at any time.

FlatHunt

MCP server by FlatHunt

Search and compare furnished apartments, studios and rooms in Berlin across multiple housing providers.

No sign-in (No account or key needed)Streamable HTTP

Connect to FlatHunt

No sign-in needed. Connect with FlatHunt’s own URL:

https://mcp.flat-hunt.com/mcp

Paste it into any client that supports remote MCP servers. Your client talks to FlatHunt directly, not through mcp.tc.

Share this server

Opens this page, with the URL and setup steps.

mcp.tc/i/flathunt

About

FlatHunt searches furnished apartments, studios, private rooms and shared rooms in Berlin from several providers. You can filter by price, size, rooms, district, availability dates, amenities and rental-policy flags, read listing details, compare listings side by side, and show listing cards in a gallery widget.

The server runs as a hosted streamable HTTP endpoint. Searching, listing details, comparison and the widget need no sign-in or API key. Saving listings and managing search alerts require signing in with OAuth.

What you can do

  • Search Berlin furnished listings with price, size, room and date filters
  • Filter by district or by coordinates and radius
  • Get full details for a single listing
  • Compare 2 to 10 listings side by side
  • Render listing cards in an interactive gallery
  • Save favourite listings and manage them (sign-in required)
  • Create and delete search alerts (sign-in required)

Tools 12

  • search_listingsRead-only

    Search furnished Berlin listings by price, size, rooms, area, dates, amenities and policy flags.

  • get_listingRead-only

    Get full details for one listing by numeric id.

  • compare_listingsRead-only

    Return normalized details for 2 to 10 listings for side-by-side comparison.

  • list_citiesRead-only

    List FlatHunt cities

  • list_areasRead-only

    List Berlin districts and neighbourhoods with canonical ids.

  • render_listings_widgetRead-only

    Return UI cards and a gallery for 1 to 10 listings.

  • list_alertsRead-only

    List the signed-in user's saved search alerts.

  • create_alertWrites

    Create a saved search alert for new matching listings.

  • delete_alertCan delete

    Delete one or more saved search alerts by id.

  • list_saved_listingsRead-only

    List the signed-in user's favourite listings.

  • save_listingWrites

    Save a listing to the user's favourites.

  • remove_saved_listingCan delete

    Remove a listing from the user's favourites.

Read from the live server on 12 Nov 2026. Read-only, Writes and Can delete are hints the server declares; your client decides whether to ask before running a tool.

Example prompts

  • Find a furnished studio in Kreuzberg under 1,200 EUR available from December

  • Compare listings 1234 and 5678 for me

  • Which Berlin districts can I filter by? Show Neukölln ids

  • Set up an alert for 2-room apartments in Mitte with Anmeldung

Set up

Every client connects to mcp.flat-hunt.com. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport http flathunt https://mcp.flat-hunt.com/mcp
  1. Start Claude Code and type /mcp. flathunt should show as connected.

Add --scope user to make it available in every project, not just this one.

Claude Desktop

  1. Open Customize → Connectors, click + Add, then Add custom connector.
  2. Name it FlatHunt and paste this URL:
https://mcp.flat-hunt.com/mcp
  1. Click Add. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

claude.ai

  1. Open the connector form on claude.ai. This button fills in the name and URL for you:
  1. Check that the URL reads https://mcp.flat-hunt.com/mcp and click Add.
  2. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.

ChatGPT

  1. On chatgpt.com, go to Plugins, select +, then Add custom MCP server.
  2. Enter a name for the server.
  3. Under Connection, paste https://mcp.flat-hunt.com/mcp as the server URL, then for authentication choose No authentication.
  4. Check I understand and want to continue, then select Create as a plugin.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "flathunt": {
      "url": "https://mcp.flat-hunt.com/mcp"
    }
  }
}

VS Code

Or from a terminal:

code --add-mcp '{"name":"flathunt","type":"http","url":"https://mcp.flat-hunt.com/mcp"}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "flathunt": {
      "type": "http",
      "url": "https://mcp.flat-hunt.com/mcp"
    }
  }
}

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "flathunt": {
      "serverUrl": "https://mcp.flat-hunt.com/mcp"
    }
  }
}
  1. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.

Codex

codex mcp add flathunt --url https://mcp.flat-hunt.com/mcp

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.flathunt]
url = "https://mcp.flat-hunt.com/mcp"

Gemini CLI

gemini mcp add --transport http flathunt https://mcp.flat-hunt.com/mcp

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.

{
  "mcpServers": {
    "flathunt": {
      "type": "http",
      "url": "https://mcp.flat-hunt.com/mcp"
    }
  }
}

Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.

Client only starts local servers? Bridge it with npx -y mcp-remote https://mcp.flat-hunt.com/mcp.

Embed

Show FlatHunt in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work

The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.

README badge

Badge preview, lightBadge preview, dark
Markdown
[![FlatHunt on mcp.tc](https://mcp.tc/i/flathunt/badge.svg)](https://mcp.tc/i/flathunt)
HTML
<a href="https://mcp.tc/i/flathunt"><img src="https://mcp.tc/i/flathunt/badge.svg" alt="FlatHunt on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/flathunt.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/flathunt" title="FlatHunt on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/flathunt.json

What each field means

AI prompt

Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the FlatHunt card to your site.

Markdown
Add the mcp.tc card for FlatHunt, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.

Put this tag where the card should appear. The card renders right before it:

```html
<script src="https://mcp.tc/w/flathunt.js" async></script>
```

To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.

```html
<div data-mcptc="flathunt"><a href="https://mcp.tc/i/flathunt">FlatHunt on mcp.tc</a></div>
```

Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.

If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).

For a README or other Markdown docs, use the badge instead:

```markdown
[![FlatHunt on mcp.tc](https://mcp.tc/i/flathunt/badge.svg)](https://mcp.tc/i/flathunt)
```

Reference: https://mcp.tc/embed

Change history

We read this server’s tool list every 3 hours and record what changes. Last read 12 Nov 2026, 11:36 UTC.

Follow FlatHunt and we’ll email you when something changes.

  1. , Automatic check

    3 tools changed.

    Details, 11 Nov 2026, 14:53 UTC

    Changed 3

    • compare_listingsoutput schema
    • get_listingoutput schema
    • search_listingsoutput schema
  2. , Automatic check

    2 tools changed.

    Details, 9 Nov 2026, 11:52 UTC

    Changed 2

    • render_listings_widgetinput schema and output schema
    • search_listingsoutput schema
  3. , Automatic check

    1 tool added and 7 tools changed. Server instructions changed.

    New server instructions

    Details, 9 Nov 2026, 02:51 UTC

    Added 1

    • list_citiesRead-only

      List the cities FlatHunt covers (Berlin plus European university cities) with the canonical `city` id to pass to search_listings and create_alert, country, currency, how many listings are live, and whether district polygons (list_areas) exist for it. Berlin is the default city: omit `city` for Berlin. Call this when the user names any other city, or asks where FlatHunt works.

    Changed 7

    • compare_listingstitle, output schema and hints

      title

      Before

      Compare Berlin listings

      After

      Compare listings

    • create_alertdescription and input schema
      Before

      Create a saved search alert so FlatHunt notifies the user about new matching Berlin listings. Accepts housing, price, size, rooms, availability, canonical area ids, amenity and rental-policy filters. Email notifications are enabled by default; Telegram too when the user has linked Telegram on FlatHunt. Requires the alerts.write scope.

      After

      Create a saved search alert so FlatHunt notifies the user about new matching listings in the chosen city (Berlin unless `city` is set). Accepts housing, price, size, rooms, availability, canonical area ids, amenity and rental-policy filters. Email notifications are enabled by default; Telegram too when the user has linked Telegram on FlatHunt. Requires the alerts.write scope.

      • New parameters: city
      • Description of areas
        Before

        Canonical Berlin area IDs from list_areas (e.g. berlin:ortsteil:prenzlauer-berg). Up to 20 IDs; multiple IDs are combined with OR. District / Ortsteil mode — do not mix with lat/lng/radiusKm. When th…

        After

        Canonical area IDs from list_areas (Berlin only, e.g. berlin:ortsteil:prenzlauer-berg). Up to 20 IDs; multiple IDs are combined with OR. District / Ortsteil mode — do not mix with lat/lng/radiusKm. W…

      • Description of postCode
        Before

        Exact Berlin post code (PLZ), e.g. 10115.

        After

        Exact post code in the searched city, e.g. 10115 (Berlin).

    • get_listingdescription, title, output schema and hints
      Before

      Get detailed information about a single FlatHunt listing in Berlin by its numeric id. Returns its description, amenities, rental-policy flags, capacity, stay terms, utilities, nearby distances, media, provider and tracking URLs. Availability and provider terms may change.

      After

      Get detailed information about a single FlatHunt listing by its numeric id (any city). Returns its description, amenities, rental-policy flags, capacity, stay terms, utilities, nearby distances, media, provider and tracking URLs. Availability and provider terms may change.

      title

      Before

      Get Berlin listing details

      After

      Get listing details

    • list_areasdescription, title, input schema, output schema and hints
      Before

      List supported Berlin districts (Bezirke) and neighbourhoods (Ortsteile) with canonical FlatHunt ids. Returns id, name, slug, type and parent area information, with optional name and type filtering. Mitte exists both as a whole Bezirk (berlin:bezirk:mitte) and as a smaller Ortsteil (berlin:ortsteil:mitte). Charlottenburg is an Ortsteil; the parent Bezirk is Charlottenburg-Wilmersdorf.

      After

      List district polygons (Berlin: Bezirke and Ortsteile) with canonical FlatHunt ids for the `areas` filter. District catalogs exist only for cities where list_cities reports hasAreas (today: Berlin, the default). For other cities search by city, post code or lat/lng/radiusKm. Returns id, name, slug, type and parent area information, with optional name and type filtering. Mitte exists both as a whole Bezirk (berlin:bezirk:mitte) and as a smaller Ortsteil (berlin:ortsteil:mitte). Charlottenburg is an Ortsteil; the parent Bezirk is Charlottenburg-Wilmersdorf.

      title

      Before

      List Berlin districts catalog

      After

      List districts catalog

      • New parameters: city
    • list_saved_listingsoutput schema
    • render_listings_widgetoutput schema
    • search_listingsdescription, title, input schema, output schema and hints
      Before

      Search current furnished apartments, studios, private rooms and shared rooms in Berlin through FlatHunt. Supports price, size, rooms, bedrooms, canonical area ids or nearby coordinates, availability dates, capacity, deposit, providers, amenity tags, rental-policy flags, sorting and pagination up to 20 results. Returns normalized listing summaries and pagination metadata. Availability, prices and provider terms may change.

      After

      Search current furnished apartments, studios, private rooms and shared rooms through FlatHunt in Berlin (default) or any city from list_cities via `city`. Supports price, size, rooms, bedrooms, canonical area ids (Berlin) or nearby coordinates, availability dates, capacity, deposit, providers, amenity tags, rental-policy flags, sorting and pagination up to 20 results. Returns normalized listing summaries and pagination metadata. Availability, prices and provider terms may change.

      title

      Before

      Search Berlin furnished listings

      After

      Search furnished listings

      • New parameters: city
      • Description of areas
        Before

        Canonical Berlin area IDs from list_areas (e.g. berlin:ortsteil:prenzlauer-berg). Up to 20 IDs; multiple IDs are combined with OR. District / Ortsteil mode — do not mix with lat/lng/radiusKm. When th…

        After

        Canonical area IDs from list_areas (Berlin only, e.g. berlin:ortsteil:prenzlauer-berg). Up to 20 IDs; multiple IDs are combined with OR. District / Ortsteil mode — do not mix with lat/lng/radiusKm. W…

      • Description of postCode
        Before

        Exact Berlin post code (PLZ), e.g. 10115.

        After

        Exact post code in the searched city, e.g. 10115 (Berlin).

    Server instructions

    Before

    You are FlatHunt's Berlin housing co-pilot: a sharp, warm, decisive friend who helps people actually find and rent furnished apartments, studios, private rooms, and shared rooms in Berlin. Guide the user from a vague need to a verified shortlist and an informed next step. Do not dump listings or let a provider link substitute for explaining a recommendation. Search, get_listing, compare, and the listings widget work without login. Save listing and create_alert require the user to be signed in (OAuth). Tone: expert friend who knows Berlin housing. Be specific, opinionated when helpful, never vague. Match the user's language. Keep replies scannable (short paragraphs, bullets for options). Celebrate good finds briefly; never hype a weak match. Never sound helpless or bureaucratic. Personalization (use conversation history + tools, never invent preferences): - Remember and reuse stated constraints: budget, rooms, move-in date, must-have amenities, commute goals, vibe (quiet / nightlife / family / students), and areas already discussed. - When authenticated, call list_saved_listings and list_alerts early if relevant — use them as taste signals; reference them naturally. - If preferences conflict with inventory, say so and propose the best trade-offs (budget bump, adjacent Ortsteil, later availableFrom). - Ask at most 1–3 clarifying questions when a search would be guesswork. Prefer searching with sensible defaults over interrogation. Filters and soft criteria: - One precise search_listings with backend filters ≫ paging then hand-filtering. Put every hard constraint in that one call (limit max 20). Paginate only when meta.totalPages > 1 and the user asks for more — never page to drop small flats or wrong districts. - Structured filters: priceMin/priceMax, squareMetersMin/squareMetersMax, rooms[] (exact OR) or roomsMin/roomsMax, bedroomsMin, areas (list_areas ids — district polygons) OR lat+lng+radiusKm (nearby; never mix geo modes), availableFrom/availableTo (YYYY-MM-DD)…

    After

    You are FlatHunt's housing co-pilot: a sharp, warm, decisive friend who helps people actually find and rent furnished apartments, studios, private rooms, and shared rooms in Berlin (the default city) and in the other European cities FlatHunt covers (list_cities: Lisbon, Porto, Madrid, Barcelona, Milan, Rome, Paris, Vienna … mostly Uniplaces student housing there). Guide the user from a vague need to a verified shortlist and an informed next step. Do not dump listings or let a provider link substitute for explaining a recommendation. Search, get_listing, compare, and the listings widget work without login. Save listing and create_alert require the user to be signed in (OAuth). Tone: expert friend who knows the local housing market. Be specific, opinionated when helpful, never vague. Match the user's language. Keep replies scannable (short paragraphs, bullets for options). Celebrate good finds briefly; never hype a weak match. Never sound helpless or bureaucratic. Personalization (use conversation history + tools, never invent preferences): - Remember and reuse stated constraints: budget, rooms, move-in date, must-have amenities, commute goals, vibe (quiet / nightlife / family / students), and areas already discussed. - When authenticated, call list_saved_listings and list_alerts early if relevant — use them as taste signals; reference them naturally. - If preferences conflict with inventory, say so and propose the best trade-offs (budget bump, adjacent Ortsteil, later availableFrom). - Ask at most 1–3 clarifying questions when a search would be guesswork. Prefer searching with sensible defaults over interrogation. Filters and soft criteria: - One precise search_listings with backend filters ≫ paging then hand-filtering. Put every hard constraint in that one call (limit max 20). Paginate only when meta.totalPages > 1 and the user asks for more — never page to drop small flats or wrong districts. - Structured filters: priceMin/priceMax, squareMetersMin/squareMetersMax…

  4. , Automatic check

    5 tools changed.

    Details, 8 Nov 2026, 17:53 UTC

    Changed 5

    • compare_listingsoutput schema
    • get_listingoutput schema
    • list_saved_listingsoutput schema
    • render_listings_widgetoutput schema
    • search_listingsoutput schema
  5. , Automatic check

    Tracking started: 11 tools.

FAQ

Can I paste mcp.tc/i/flathunt into my MCP client?

No. mcp.tc links are pages, not server addresses. Connect with https://mcp.flat-hunt.com/mcp, so your client talks to FlatHunt directly. The quick link is for sharing: it opens this page, with setup steps for every client.

Does FlatHunt need an API key or a sign-in?

No. FlatHunt doesn’t ask for an account or key.

Is FlatHunt a remote or a local server?

Remote. FlatHunt hosts it at https://mcp.flat-hunt.com/mcp, and it speaks Streamable HTTP. There’s nothing to install.

What can FlatHunt do?

It has 12 tools, including search_listings, get_listing and compare_listings. You can search Berlin furnished listings with price, size, room and date filters, filter by district or by coordinates and radius and get full details for a single listing.

Which clients can use it?

Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.

Does mcp.tc track changes to FlatHunt?

Yes. FlatHunt’s History tab shows each change we find to its tools, down to descriptions and parameters, plus new versions and edits by its owner. Follow the listing to get an email when it changes.

Who wrote this page?

mcp.tc’s robot read FlatHunt’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

mcp.tc isn’t affiliated with FlatHunt. This page was built from FlatHunt’s public metadata, last checked on 12 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.