Property Finder MCP Server

Listings, leads and credits in your Property Finder broker account.

Hosted MCP Server

npx add-mcp 'https://cotlet.dev/mcp/v1/property-finder'

Installs into Claude Code, Codex, Cursor and more

Documentation

Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up

Property Finder API and MCP server

Property Finder has an API, but only for software partners it approves through the PF Developer Network, not for brokers directly (checked 11 Oct 2026). Partners pass a business review and a security and compliance audit, and each PF Expert client then chooses to authorize them.

Listings, leads and credits in your Property Finder broker account. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.

MCP setup REST API guide

Property portal for the UAE and the wider Middle East, where agencies and agents publish listings and receive leads through PF Expert.

What is the Property Finder API?

Cotlet's Property Finder API exposes 11 endpoints for your own Property Finder account: list listings, get listing, get listing stats, list leads, list agents, get credits, create listing, update listing, publish listing, unpublish listing and upgrade listing. The list_listings endpoint returns listings in your agency with status, agent, price, quality score and active upgrade. Each endpoint takes simple JSON inputs like listing_id, agent_id or purpose and works both as an operation of the property_finder_read or property_finder_write MCP tool for agents and as a REST call for scripts.

  • Category: Real estate
  • Endpoints: 11 (6 read, 5 write)
  • Updated: 2026-11-15

Property Finder has an API, but only for software partners it approves through the PF Developer Network, not for brokers directly (checked 11 Oct 2026). Cotlet is a hosted MCP server and REST API for Property Finder with 11 endpoints (6 read, 5 write): you sign in once in your own cloud browser, your AI agent does the work.

Does Property Finder have an official API?

Property Finder has an API, but only for software partners it approves through the PF Developer Network, not for brokers directly (checked 11 Oct 2026). Partners pass a business review and a security and compliance audit, and each PF Expert client then chooses to authorize them.

TaskProperty Finder officialCotlet
List listings with status and quality scorePartly: Approved partners onlyYes
Create and publish a listingPartly: Approved partners onlyYes
Unpublish a listingPartly: Approved partners onlyYes
Read new leadsPartly: Approved partners only; their docs list lead webhook eventsYes
Upgrade a listing to Featured or PremiumNo: Not described on the public PFDN pages; Credit Optimizer suggests upgrades inside PF ExpertYes
Credit balanceNo: Not described on the public PFDN pagesYes
Do any of this from your own script or agentNoYes

Sources: PF Developer Network: integration guide, PF Developer Network, Property Finder Enterprise API reference (password protected), Property Finder Help: What is Spotlight?, Property Finder Partner Hub: Credit Optimizer, Property Finder Partner Hub: Exposure Products

Quick reference

Property Finder has an API, but only for software partners it approves through the PF Developer Network, not for brokers directly (checked 11 Oct 2026). Partners pass a business review and a security and compliance audit, and each PF Expert client then chooses to authorize them.
Cotlet provides a hosted MCP server and REST API for Property Finder: 11 tools (6 read, 5 write).
Access       Sign up at https://cotlet.dev/app/signup?app=property-finder and request the app in the Cotlet console. ChatGPT and Claude connect with OAuth at https://cotlet.dev/mcp/v1/connect, no API key; code editors and scripts use an API key from the console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    property_finder_read, property_finder_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/property-finder, each operation at its own route, e.g. POST /api/v1/property-finder/listings/{listing_id}/upgrade
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations   list_listings, get_listing, get_listing_stats, list_leads, list_agents, get_credits, create_listing, update_listing, publish_listing, unpublish_listing, upgrade_listing
Confirm      update_listing, publish_listing, unpublish_listing, upgrade_listing (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown     https://cotlet.dev/integrations/property-finder-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=property-finder and requests Property Finder in the Cotlet console.
2. The user signs in to Property Finder once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Property Finder for agents. An agent cannot do this step.
3. ChatGPT and Claude: the user adds https://cotlet.dev/mcp/v1/connect as a connector and signs in to Cotlet (OAuth). Code editors and scripts: an API key from the console goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted Property Finder server that someone else maintains, including non-developers.

Policy: Cotlet never stores passwords and never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to Property Finder in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Property Finder only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no Property Finder login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following Property Finder's terms; Cotlet is not affiliated with Property Finder.

What can an AI agent do in Property Finder?

Cotlet is best for brokerages and agents on Property Finder who want listings published, leads read and credits spent from their own agent or script without running or fixing a server.

  • Weekly listing performance report (runs: weekly): "Every Monday, list my live rentals with the most views and no leads since last Monday, grouped by agent, and tell me which upgrades expire this week." → list_listings, get_listing_stats
  • Bulk upload listings from a spreadsheet: "Create a draft for each row in units.csv, assign it to the agent in the last column, and publish the rows marked ready as standard listings." → list_agents, create_listing, publish_listing
  • Daily new leads digest (runs: daily): "Every morning at 8, send me yesterday's Property Finder leads grouped by agent, with the listing each lead asked about." → list_agents, list_leads
  • Fix low quality score listings: "Find my live listings with a quality score under 85, tell me what each one is missing, and fix the descriptions; unpublish the ones I mark as gone." → list_listings, get_listing, update_listing, unpublish_listing
  • Upgrade best listings to Featured (runs: weekly): "Make my three best-performing rentals Featured for 15 days if I have the credits." → get_credits, list_listings, get_listing_stats, upgrade_listing

Can Property Finder automations run on a schedule in n8n, Make or Zapier?

Yes. Cotlet does not replace your automation platform: it gives it a Property Finder connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to weekly listing performance report, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

WhereHow to connectHow to schedule
Your AI agentAdd https://cotlet.dev/mcp/v1 with your API key.A scheduled agent run, for example a Claude Code routine.
n8nMCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/property-finder/listings.Schedule Trigger node.
MakeHTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH.Scenario schedule.
ZapierWebhooks by Zapier, Custom Request: the same method, URL, header and body.Schedule by Zapier trigger.
Your own scriptGET https://cotlet.dev/api/v1/property-finder/listings with your API key.cron or GitHub Actions.

Tools

For AI agents: Every endpoint and its schema is public. The 11 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Property Finder.

list_listings

Listings in your agency with status, agent, price, quality score and active upgrade. Access: read. REST: GET /api/v1/property-finder/listings. MCP: property_finder_read → list_listings.

ParameterTypeRequiredDescription
statusenumnolive, draft or unpublished. Default: live.
agent_idstringnoOnly listings assigned to this agent, from list_agents.
purposeenumnosale or rent.
max_quality_scoreintegernoOnly listings at or under this quality score, 0 to 100.
limitintegerno1 to 100. Default: 50.
cursorstringnoNext page cursor from the previous call.

Returns listings of your agency, newest first. Quality score is the percentage PF Expert shows for a published listing. Pages hold up to 100 listings; pass next_cursor back as cursor for the next page.

Example response:

{
  "listings": [
    {
      "listing_id": "01JA7K3M9Q",
      "title": "Furnished 2BR with marina view",
      "purpose": "rent",
      "status": "live",
      "agent_id": "ag_3d91",
      "price": 145000,
      "quality_score": 88,
      "upgrade": "featured"
    },
    {
      "listing_id": "01JA8B2N4R",
      "title": "Studio near the metro",
      "purpose": "rent",
      "status": "live",
      "agent_id": "ag_77c2",
      "price": 62000,
      "quality_score": 64,
      "upgrade": null
    }
  ],
  "next_cursor": null
}

get_listing

Full listing: title, description, location, specs, price, images, permit number and quality score. Access: read. REST: GET /api/v1/property-finder/listings/{listing_id}. MCP: property_finder_read → get_listing.

ParameterTypeRequiredDescription
listing_idstringyesListing ID from list_listings.

Returns everything PF Expert holds for one listing, including the permit number if you entered one. Use it to see why a quality score is low before you change anything. A draft has no quality score yet.

Example response:

{
  "listing_id": "01JA8B2N4R",
  "title": "Studio near the metro",
  "purpose": "rent",
  "status": "live",
  "property_type": "Apartment",
  "location": "Business Bay",
  "price": 62000,
  "bedrooms": 0,
  "size_sqft": 410,
  "description": "Bright studio, close to the metro.",
  "image_urls": [
    "https://example.com/photos/studio-1.jpg"
  ],
  "permit_number": null,
  "agent_id": "ag_77c2",
  "quality_score": 64
}

get_listing_stats

Views and leads for one listing since a date. Access: read. REST: GET /api/v1/property-finder/listings/{listing_id}/stats. MCP: property_finder_read → get_listing_stats.

ParameterTypeRequiredDescription
listing_idstringyesListing ID from list_listings.
sincedatenoCount from this date. Default: 30 days ago.

Returns the performance numbers PF Expert shows for one listing, from the start date to now. Call it once per listing, so keep the set small and filter with list_listings first. A listing that went live after the start date counts from its publish date.

Example response:

{
  "listing_id": "01JA7K3M9Q",
  "since": "2026-09-11",
  "views": 1840,
  "leads": 0
}

list_leads

Leads from your listings, newest first, with contact, listing, agent and time received. Access: read. REST: GET /api/v1/property-finder/leads. MCP: property_finder_read → list_leads.

ParameterTypeRequiredDescription
sincedatetimenoOnly leads received after this time.
listing_idstringnoOnly leads for this listing.
agent_idstringnoOnly leads for this agent.
limitintegerno1 to 100. Default: 50.
cursorstringnoNext page cursor from the previous call.

Returns leads that came in through your listings, newest first. Each lead names the listing and the agent it belongs to. Pages hold up to 100 leads; pass next_cursor back as cursor for the next page.

Example response:

{
  "leads": [
    {
      "lead_id": "ld_90f1",
      "name": "Jamie Hart",
      "phone": "+971500000000",
      "listing_id": "01JA7K3M9Q",
      "agent_id": "ag_3d91",
      "received_at": "2026-10-10T16:42:00+04:00"
    }
  ],
  "next_cursor": null
}

list_agents

Agents in your agency with their IDs and number of listings. Access: read. REST: GET /api/v1/property-finder/agents. MCP: property_finder_read → list_agents.

No parameters.

Returns the agents of your agency. Use agent_id from here to assign a listing or to filter listings and leads. You see the agents your own role can see in PF Expert.

Example response:

{
  "agents": [
    {
      "agent_id": "ag_3d91",
      "name": "Sara Khan",
      "listings": 24
    },
    {
      "agent_id": "ag_77c2",
      "name": "Omar Haddad",
      "listings": 11
    }
  ]
}

get_credits

The credit balance PF Expert shows for your agency. Access: read. REST: GET /api/v1/property-finder/credits. MCP: property_finder_read → get_credits.

No parameters.

Returns the credits available for upgrades. Check it before upgrade_listing so the agent does not plan a spend you cannot cover. It reads the balance only and spends nothing.

Example response:

{
  "credits": 2500
}

create_listing

New draft listing in PF Expert. Nothing goes live until you publish it. Access: write. REST: POST /api/v1/property-finder/listings. MCP: property_finder_write → create_listing.

ParameterTypeRequiredDescription
titlestringyesListing title.
purposeenumyessale or rent.
property_typestringyesAs in PF Expert, e.g. Apartment or Villa.
locationstringyesCommunity or building, matched to the Property Finder location list.
priceintegeryesPrice as you enter it in PF Expert.
bedroomsintegernoNumber of bedrooms, 0 for a studio.
bathroomsintegernoNumber of bathrooms.
size_sqftintegernoBuilt-up area in square feet.
descriptionstringnoListing description.
image_urlsstring[]noImage URLs, first one is the cover.
permit_numberstringnoPermit number, where PF Expert asks for one.
agent_idstringnoAssigned agent, from list_agents.

Saves a draft in PF Expert and returns its listing_id. The draft is visible only to you and your agency. It reaches no one and you can delete it in PF Expert, so it does not ask for confirmation. Run publish_listing to put it live.

Example response:

{
  "listing_id": "01JA9C5P7T",
  "status": "draft",
  "agent_id": "ag_3d91"
}

update_listing

Change the price, description, images, permit or agent of a listing. Access: write, asks the user first. REST: PATCH /api/v1/property-finder/listings/{listing_id}. MCP: property_finder_write → update_listing.

ParameterTypeRequiredDescription
listing_idstringyesListing ID from list_listings.
fieldsobjectyesAny of the create_listing fields.

Applies the fields you pass and leaves the rest as they are. Changes to a live listing are visible to buyers and renters, and PF Expert may recalculate the quality score. Returns the updated fields. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "listing_id": "01JA8B2N4R",
  "updated": [
    "description",
    "image_urls"
  ],
  "quality_score": 72
}

publish_listing

Put a draft or unpublished listing live on Property Finder. Access: write, asks the user first. REST: POST /api/v1/property-finder/listings/{listing_id}/publish. MCP: property_finder_write → publish_listing.

ParameterTypeRequiredDescription
listing_idstringyesListing ID from list_listings.
listing_typeenumyesstandard, featured or premium.
durationenumno15_days or 1_month for featured and premium. Standard runs 1 month.

Publishes the listing with the listing type you choose on the Publish screen of PF Expert: standard, featured or premium. Featured and premium run for 15 days or 1 month; the options your market shows may differ. It returns the live status and the portal URL. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "listing_id": "01JA7K3M9Q",
  "status": "live",
  "listing_type": "standard",
  "url": "https://www.propertyfinder.ae/en/plp/rent/apartment-for-rent-dubai-dubai-marina-01JA7K3M9Q.html"
}

unpublish_listing

Take a live listing off the portal. It stays in PF Expert. Access: write, asks the user first. REST: POST /api/v1/property-finder/listings/{listing_id}/unpublish. MCP: property_finder_write → unpublish_listing.

ParameterTypeRequiredDescription
listing_idstringyesListing ID from list_listings.

Removes the listing from Property Finder search and keeps it in PF Expert with status unpublished, so you can publish it again later. Leads already received stay in your leads. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "listing_id": "01JA8B2N4R",
  "status": "unpublished"
}

upgrade_listing

Apply Featured or Premium to a live listing. Uses credits. Access: write, asks the user first. REST: POST /api/v1/property-finder/listings/{listing_id}/upgrade. MCP: property_finder_write → upgrade_listing.

ParameterTypeRequiredDescription
listing_idstringyesListing ID from list_listings.
listing_typeenumyesfeatured or premium.
durationenumyes15_days or 1_month.

Upgrades a live listing to featured or premium for 15 days or 1 month and pays with credits. It returns the expiry date and the credits left. Spotlight is a bidding product and is not covered by this tool. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "listing_id": "01JA7K3M9Q",
  "status": "live",
  "listing_type": "featured",
  "expires_at": "2026-10-26T12:00:00+04:00",
  "credits_left": 2380
}

How do I connect Property Finder to ChatGPT, Claude, Cursor or Codex?

Connecting Property Finder takes three steps: sign up, sign in to Property Finder once in your Cloud Browser and enable it for agents, then add Cotlet to ChatGPT or Claude as a connector, with no API key, or add one MCP server or call the REST API with an API key.

Connect Property Finder to your agent.

  1. Create an account Sign up and add Property Finder in the console. ChatGPT and Claude need no API key: you sign in to Cotlet when you add the connector. Code editors and scripts take an API key from the console.

  2. Sign in to Property Finder in your Cloud Browser Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Property Finder there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.

  3. Add Cotlet to ChatGPT, Claude or your agent Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

    ChatGPT:

Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth

Claude:

Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect

Claude Code:

claude mcp add --transport http cotlet \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"

Cursor:

{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}

Codex:

# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
  1. Ask your agent Ask in plain words. Your agent finds the Property Finder tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.
Every Monday, list my live rentals with the most views and no leads since last Monday, grouped by agent, and tell me which upgrades expire this week.

Call Property Finder from your scripts.

  1. Export your API key Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.
export COTLET_API_KEY="cotlet_..."
  1. Call a tool Every tool is an endpoint under /api/v1/property-finder with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.
curl -X POST https://cotlet.dev/api/v1/property-finder/listings/01JA7K3M9Q/upgrade \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"listing_type":"featured","duration":"15_days"}'
  1. Read the result You get plain JSON back, ready for your script. A failed call costs nothing.
{
  "listing_id": "01JA7K3M9Q",
  "status": "live",
  "listing_type": "featured",
  "expires_at": "2026-10-26T12:00:00+04:00",
  "credits_left": 2380
}

How to use the Property Finder REST API

Create your Cotlet API key

Create a Cotlet API key with access to Property Finder and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.

Connect Property Finder in Cotlet and enable it for agents. Account access: Your own PF Expert account (agency admin or agent), email and password.

Make your first Property Finder API request

REST:

curl https://cotlet.dev/api/v1/property-finder/listings \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read listings and apply the operation limits

A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.

Illustrative response excerpt:

{
  "status": "success",
  "app": "property-finder",
  "tool": "list_listings",
  "result": {
    "listings": [
      {
        "listing_id": "01JA7K3M9Q",
        "title": "Furnished 2BR with marina view",
        "purpose": "rent",
        "status": "live",
        "agent_id": "ag_3d91",
        "price": 145000,
        "quality_score": 88,
        "upgrade": "featured"
      },
      {
        "listing_id": "01JA8B2N4R",
        "title": "Studio near the metro",
        "purpose": "rent",
        "status": "live",
        "agent_id": "ag_77c2",
        "price": 62000,
        "quality_score": 64,
        "upgrade": null
      }
    ],
    "next_cursor": null
  }
}

Returns listings of your agency, newest first. Quality score is the percentage PF Expert shows for a published listing.

Pages hold up to 100 listings; pass next_cursor back as cursor for the next page.

limit: 1 to 100. Default: 50.

cursor: Next page cursor from the previous call.

Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.

Property Finder workflows for agents and automations

ToolConnect throughExample workflow
n8nHTTP RequestViews and leads for one listing since a date. Use get_listing_stats in your configured property report.
MakeHTTP > Make a requestLeads from your listings, newest first, with contact, listing, agent and time received. Use list_leads in your configured property report.
Python or Node.jsREST APIAgents in your agency with their IDs and number of listings. Use list_agents in your configured property report.

Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.

Cotlet reads Property Finder; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.

Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.

The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.

Why use Cotlet for Property Finder?

Built for agents

  • One MCP server for every app you connect.
  • The same tools as a REST API for scripts and cron jobs.
  • Works with ChatGPT, Claude, Claude Code, Codex and Cursor.

Your login stays yours

  • You sign in to Property Finder yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
  • A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
  • The model never sees a login.
  • No stored passwords, no MFA bypass.

You stay in control

  • Scope each API key: its apps, its tools, read only or read and write.
  • Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
  • Every background request listed in your Background activity. Disable for agents in one click.

Kept working for you

  • We test every integration every 6 hours.
  • When Property Finder changes, the tool pauses until we fix it.
  • Failed calls cost nothing.

Is it safe to connect Property Finder to Cotlet?

Yes. You sign in to Property Finder yourself, in your own Cloud Browser, and we never save your password. Your agents only get Property Finder once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.

  • A+ on Qualys SSL Labs: Encryption in transit: TLS setup and certificates, on all four server addresses. Live result
  • A+ on securityheaders.com: Browser protections sent with every page, all six headers present. Live result
  • A+ on Mozilla Observatory: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. Live result
  • Clean on Sucuri SiteCheck: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. Live result

How Cotlet protects your access

Common concerns

Who runs Cotlet?

Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.

Is this an official Property Finder integration?

No, Cotlet is independent of Property Finder. Property Finder's own API is open only to approved partners. Cotlet works through your own Property Finder account, the way you use Property Finder in the browser, so you need no partner approval and no developer setup.

What about client data and GDPR?

Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.

Can I start with read only?

Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.

Is it reliable?

Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.

How do I stop?

Press Disable for agents next to Property Finder in your console: your agents lose access at once and you stay signed in. Signing out of Property Finder in the browser works too, and Reset browser deletes the whole profile.

Is there a Property Finder MCP server on GitHub?

Brokers reach PF Expert from code through a partner CRM that PFDN has approved. Hosted scrapers only read public listings. For your own agent or script there is no direct route.

Partner CRMCotlet
SetupMove to an approved CRM, ask Property Finder to authorize it for your agency, map your listingsSign up, sign in to PF Expert once in your Cloud Browser
Where it runsInside the CRM screensHosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule
Write actionsWhatever the CRM vendor built for youPublish, unpublish, upgrade and edit from a prompt or a script, each confirmed by you by default
When the session expiresThe CRM keeps its own authorizationIf PF Expert logs you out, your agent gets a link to sign in again
When Property Finder changesThe CRM vendor adaptsOur team tests it daily and fixes it; failed calls are free
UpkeepYou depend on the vendor roadmapNothing to host or update
PriceCRM subscription, set by the vendorFree 7-day trial, then pay-as-you-go credit packs, no subscription

Which one fits you

Pick Cotlet if

  • you are not a developer, or you do not want to maintain a server
  • you need it to keep working when Property Finder changes, without checking it yourself
  • your agent or a script should run it on a schedule, also while your computer is off

Pick an open-source server if

  • you are comfortable installing, updating and fixing it yourself
  • you want your sign-in to stay on your own computer
  • you only need it now and then, from one MCP client

How much does the Property Finder API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Property Finder API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 10 to 100 credits (10 for most tools, about $0.04 to $0.06), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.

CreditsPrice, one timeCalls at 10 creditsPer 1,000 credits
5,000$29500$5.80
15,000$791,500$5.27
32,000$1493,200$4.66
60,000$2496,000$4.15

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the Authorization: Bearer header. See full pricing

How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Property Finder account.

  • Company details: Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. Terms of service
  • Your sign-in: You sign in to Property Finder yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Property Finder only after you enable it. When Property Finder signs you out, your agent gives you a link to sign in again. Security
  • Revoking access: Press Disable for agents next to Property Finder, sign out of Property Finder in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
  • What we never do: Store passwords or bypass MFA.
  • Property Finder's terms: You use your own Property Finder account and stay responsible for following Property Finder's terms. Cotlet is independent and not affiliated with Property Finder. Terms
  • Contact: Questions about the company, security or an app: contact@cotlet.dev

Also listed on: Odel, mcpbeat

Property Finder API and MCP: questions

How do I get access?

Sign up free, open Property Finder in the console and press Activate. Then you create your API key and connect Property Finder there.

Do I need to be technical?

No. You sign in to Property Finder once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.

Is it safe to connect Property Finder to Cotlet?

Yes. You sign in to Property Finder yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Property Finder once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.

Is a hosted server safer than a local one? My Property Finder sign-in would leave my computer.

On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Property Finder cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.

Why does Cotlet send requests instead of clicking in my browser?

To be fast, Cotlet doesn't click through Property Finder's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Property Finder sees the same browser and IP you signed in with, and every request is listed in your Background activity.

What if someone gets my Cotlet API key?

The key holds no Property Finder login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.

Why a signed-in browser and not OAuth, like other integration platforms?

Property Finder offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).

How do I connect Property Finder to ChatGPT or Claude?

Sign up at cotlet.dev, log in to Property Finder once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your Property Finder account through Cotlet, in their phone apps too.

What can ChatGPT do in Property Finder?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Property Finder: weekly listing performance report; bulk upload listings from a spreadsheet; daily new leads digest. You ask in plain words, and anything that reaches other people waits for your OK first.

Do I need to be a PF Developer Network partner to use Cotlet?

No. PFDN is a program for software vendors who build integrations for many clients. Cotlet signs in to your own PF Expert account, the way you do, and you can revoke it at any time (checked 11 Oct 2026).

Can it bid for Spotlight?

Not in these tools. Property Finder describes Spotlight as a bid for the top three search positions for one week. A listing must be published less than 60 days ago, have a quality score of at least 90%, be Premium and have enough credits (Property Finder Help, checked 11 Oct 2026).

Can my agent post or send messages in Property Finder without asking me?

No. Every call to update_listing, publish_listing, unpublish_listing or upgrade_listing waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. create_listing runs without asking, because it sends nothing to anyone and one call undoes it.

Can I use the Property Finder API in n8n?

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/property-finder from the HTTP Request node.

Can I use the Property Finder API without an AI agent?

Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.


Give your AI agents your signed-in browser.

Product: Integrations · How it works · Pricing · Security

Resources: Blog · API docs · Help center · Changelog · GitHub

Solutions: For developers · For automation agencies

Company: About · AI info: company facts · Contact

Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors

Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub

Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.