Allows ordering paid services via Stripe, generating Stripe checkout URLs for instant products and processing card payments on-platform.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@@marocain/mcp-server search for a luxury villa in Marrakech with a high GIN score"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
The official Model Context Protocol server for marocain.investments — bringing {GIN}, our authored real-estate intelligence for Morocco, into any MCP client (Claude Desktop, IDEs, agents).
Discover, score and analyse Moroccan luxury real estate — then submit an enquiry that's routed on-platform. All the analysis is free; contact with the agent is always intermediated by the platform.
{GIN} is the platform's proprietary scoring DNA. Instead of one blurry "AI score", it speaks with two coherent pillars fused into one honest verdict:
{GIN} Quality — how good the asset is (vision view/structural/condition + location + yield + WC 2030 catalyst + trust).
{GIN} Deal — how good the buy is (asking price vs. the M-Value AVM, adjusted for city momentum).
Fused verdict — one buy/hold/pass headline that can never disagree with the numbers ("Prime asset, priced to buy", "Cheap — verify condition", …).
It's the difference between a good property and a good deal — the question generic scores never answer. It's honest by design: an overpriced listing is told it's overpriced.
Related MCP server: Israel Real Estate MCP
No install needed — run it straight from npm:
npx -y @marocain/mcp-serverAdd to claude_desktop_config.json:
{
"mcpServers": {
"marocain": {
"command": "npx",
"args": ["-y", "@marocain/mcp-server"]
}
}
}Fourteen tools — eleven read-only analysis tools (sale and rental), a moat-safe enquiry tool, and two commerce tools (discover + order paid services).
Tool | What it does |
| Search AI-graded Moroccan for-sale listings by city, typology, price, rooms, free-text. |
| Full detail for one listing — price (USD/MAD), AI scores, M-Value AVM, trust, {GIN} pillars + verdict. |
| The {GIN} verdict: Quality + Deal pillars + the fused buy/hold/pass headline. |
| Macro market facts for a city or national scope (median price, supply, momentum, WC 2030 / TGV catalysts). |
| AI-derived one-paragraph investment memo for a listing (6 languages). |
| Conceptual / vector search across the catalogue and the authored guides (Foreign Buyer's Playbook, Morocco-vs-Dubai, AI-scoring methodology, residency, city theses). |
| Ask T{AI]GIN, the agentic investment analyst, a one-shot question — it plans, searches, scores with the {GIN} pillars and answers with citations. |
| A structured, honest investor deal memo for one listing (verdict, M-Value, yield, strengths, risks, district read, next steps). |
Tool | What it does |
| Search AI-graded Moroccan long-let rentals (residential / commercial / student) by city, typology, monthly-rent band (MAD or USD) and tier. Rent in MAD/month; never returns landlord/agency contact. |
| How much monthly rent a net income comfortably supports — the same rent ≤ 33% of net income rule as /finance. Income in MAD or USD. |
| Compare the monthly cost of buying vs renting a property — same mortgage annuity engine as /finance (30% down · 20y · 5.2% defaults, all overridable). Principal + interest only. |
Tool | What it does |
| Submit a buyer enquiry / request a viewing — routed on-platform to the listing's verified agent. Returns a reference, never any contact. |
| The transactable service catalogue + EUR prices — buyer services (AI staging, viral content, reservation, appraiser, visitation — note the live API |
| Order any service. Instant products return a Stripe |
Payments: card checkout for instant products may be briefly unavailable while the platform reconnects its payment processor — request-based services and buyer enquiries work regardless.
order_servicereports this cleanly.
The model is simple and the same for everyone: all the intelligence is free (it's lead-gen), and the only way to make contact is through the platform (that's the moat, and how agents are billed).
Discover & score with search_listings / get_gin_score / semantic_search.
Go deep with get_listing / gin_deal_memo / gin_ask.
Enquire with request_service — it routes the buyer's interest to the listing's verified agent and returns a reference. You never receive the agent's phone, email or WhatsApp; the platform intermediates contact.
Most of the catalogue is still being onboarded by agents.
request_serviceroutes to a listing's claimed, verified agent; for a listing without one yet it returns a clear note instead of routing.
get_gin_score({ id }) → the authored verdict:
{
"id": "…",
"title": "…",
"price_usd": 9630000,
"gin_verdict": { "key": "prime_value", "label": "Prime asset, priced to buy", "tone": "strong" },
"gin_quality": 76,
"gin_deal": 64,
"m_value_usd": 9100000,
"trust": { "title_verified": false, "fcr_status": "unknown" }
}request_service({ listing_id, buyer_name, buyer_email, message }) → an on-platform reference, no contact:
{ "ok": true, "kind": "lead", "lead_id": "…", "status": "requested", "routed": true }No tool ever returns an agent's, landlord's or seller's contact. On top of the public API hiding the phone, this server redacts the origin-portal deep link (source_url / source_listing_id) and the agent / agency name from listing payloads — so a downstream agent can't route a user off-platform to the seller. Rentals (search_rentals) are read through the site's public, anon-granted rental_browse RPC, which is SECURITY DEFINER, scrubs PII in SQL and whose return signature carries no contact / source fields at all; the result still passes through the same central stripMoat() as every other tool. The single conversion path is request_service, which routes a buyer enquiry through marocain's own lead flow and returns a reference, never any contact. Discover, score and analyse freely; contact is always intermediated by the platform.
Symptom | Cause | Fix |
| Upstream slow or unreachable. | Retry. Bump |
| Rare — Vercel platform-level anti-bot on very bursty traffic. | Back off and retry. |
| A buyer name + valid email are mandatory so the agent can reply. | Supply both. |
| The listing has no claimed agent yet, so the enquiry can't be routed. | Try a claimed/verified listing; check back as agents onboard. |
| You set | Leave it unset (the default is correct). |
Env var | Default | Purpose |
|
| Override the API origin (testing only; must be HTTPS + allowlisted). |
|
| Per-request upstream timeout. |
Skills catalog: @hei33enberg/luxury-skills (npm) — the machine-readable capability catalog this server draws from.
Live API: https://marocain.investments/api/public/* · AEO manifest: /llms.txt.
Publishing to npm is automated by a GitHub Action (publish-mcp) in the platform repo:
# bump the version, commit, push — the Action publishes @marocain/mcp-server
npm version patch # or minor / major (edits package.json)
git push --follow-tagsLocal npm test runs the unit tests (CI runs them on Node 18/20/22); CI additionally runs the black-box MCP handshake smoke (node test/smoke.mjs) on Node 20.
MIT © marocain.investments
The {GIN} coherent verdict for a listing: the Quality pillar (asset, compute_marocain_score), the Deal pillar (price-vs-AVM + momentum) and the one fused buy/hold/pass verdict. The authored number an investor can defend.
Inputs: id (required).
Full detail for one listing by id: price (USD/MAD), AI scores, M-Value AVM, FCR/title trust, source provenance and the {GIN} pillars + verdict. Never returns the agent's phone.
Inputs: id (required).
Macro market facts for a city or national scope — median price, supply, momentum and the catalysts (WC2030, TGV) the {GIN} Deal pillar is benchmarked against.
Inputs: scope (required).
Ask T{AI]GIN — the {GIN} agentic investment analyst — a one-shot natural-language question. It plans, searches the catalogue + authored guides, scores with the {GIN} pillars and answers grounded with citations. Use for open questions ('which Tangier district has the best rental upside?', 'why Morocco over Dubai?'). Never returns agent contact details.
Inputs: q (required).
Generate a structured investor DEAL MEMO for one listing id: the {GIN} Quality + Deal verdict, M-Value AVM with value-vs-ask, gross yield, strengths, risks, district read and next steps. Honest (won't soften an overpriced verdict). Decision support, not a certified appraisal.
Inputs: listing_id (required).
AI-derived investor narrative for a listing — a one-paragraph thesis synthesising the {GIN} pillars, financial vision and location into a single decision memo.
Inputs: listing_id (required), lang.
List the platform's transactable services + EUR prices — for BUYERS (AI staging, viral content, refundable reservation, bank-honored appraiser, on-site visitation, the €199 AI business-model plan, plus request-only lawyer / financing / bespoke commercialization) and for AGENTS/sellers (listing boost, photo relight). Returns each product_type + its variant ids + price, which order_service needs. NOTE: card checkout for instant products may be temporarily unavailable while the payment processor is being reconnected; request-based services and buyer enquiries work regardless.
Inputs: no named parameters.
Place an order for any platform service (a product_type + variant from list_services). Instant products return a Stripe checkout_url to complete payment on-platform; request-only products (lawyer, financing, commercialization, contact) return a tracked order_id with no upfront charge. Requires the buyer's email. NEVER returns agent/seller contact. For a plain buyer enquiry to a listing's agent, prefer request_service.
Inputs: variant (required), buyer_email (required), product_type (required), message, +3 more.
How much monthly rent a given net income comfortably supports. Uses the SAME rule-of-thumb as marocain.investments/finance (rent ≤ 33% of net monthly income) so the answer never disagrees with the website. Give income in MAD (net_monthly_income_mad) or USD (net_monthly_income_usd). Returns the comfortable rent ceiling in MAD and USD.
Inputs: net_monthly_income_mad, net_monthly_income_usd.
Compare the monthly cost of BUYING a property vs RENTING it. Uses the SAME mortgage engine as marocain.investments/finance (standard annuity payment on the loan after down payment) — principal + interest only, excluding insurance/fees/taxes/maintenance/appreciation. Defaults mirror the site: 30% down, 20-year term, 5.2% rate. Returns the monthly buy payment, the rent, and the monthly difference (buy − rent).
Inputs: price_mad (required), monthly_rent_mad (required), down_pct, term_years, +1 more.
Submit a buyer ENQUIRY (or request a viewing / valuation / financing / renovation / legal help) for a listing. This is the ONLY conversion path: it routes the enquiry through marocain.investments to the listing's verified agent and returns a confirmation reference — it NEVER returns the agent's contact (the platform intermediates all contact). Works for listings that have a claimed, verified agent; for not-yet-claimed scraped listings it returns a clear note instead of routing. Requires the buyer's name + email so the agent can follow up.
Inputs: buyer_name (required), listing_id (required), buyer_email (required), message, +2 more.
Search AI-graded Moroccan luxury listings by city, typology, price, rooms and a free-text query. Returns structured listings with prices and {GIN} scores. Never returns agent contact details.
Inputs: q, city, limit, typology, +3 more.
Search AI-graded Moroccan long-let RENTAL listings (residential / commercial / student) by city, typology, monthly rent band and tier. Rent is in MAD/month (rent_usd_month provided too). Returns structured rentals with {GIN} scores. Calls the same public, PII-scrubbed rental surface the website uses — NEVER returns landlord/agency contact. Note: unlike sale search there is no server-side rooms or free-text filter on the public rental surface (rooms is returned per listing); filter by city / typology / rent band / tier.
Inputs: city, sort, tier, limit, +6 more.
Semantic / conceptual vector search across the Moroccan catalogue AND the authored guides (Foreign Buyer's Playbook, Morocco-vs-Dubai thesis, AI scoring methodology, residency, city theses). Use for fuzzy / lifestyle / thesis queries that don't map to exact filters — e.g. 'quiet authentic seaside neighbourhood with rental upside' or 'why Morocco over Dubai'. Returns ranked items with a similarity score. Never returns agent contact details.
Inputs: q (required), k, types.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 14 tools
Tools are mostly distinct: search vs. get vs. generate vs. service actions are clear. The main potential confusion is among the listing-centric tools (get_listing, get_gin_score, gin_deal_memo, listing_derive) which all operate on a single listing but produce different outputs. Descriptions do clarify the differences, but an agent might still hesitate when choosing between them.
Names mostly follow verb_noun pattern (search_listings, get_listing, list_services), but a few like listing_derive, gin_ask, gin_deal_memo break the pattern with noun_verb. Still, all names are descriptive and use a consistent snake_case style, so the deviation is minor.
14 tools is within the ideal range (3-15). Each tool covers a distinct aspect of the real estate investment workflow: search, detail, score, memo, market data, services, and financial calculators. No tool feels redundant.
The surface covers the full investor journey: discover (search), evaluate (get_listing, get_gin_score, gin_deal_memo, listing_derive), understand market (get_market), calculate (rent_affordability, rent_vs_buy), and act (request_service, order_service, list_services). Also includes semantic search and an agentic Q&A. No obvious gaps for the stated purpose.
Real estate MCP server for Morocco — search, valuation, market analysis, 17 tools.
MCP server for VC pitch-deck scoring, thesis-fit matching, and deal-flow management.
MCP server for real-estate agents: listings, CRM, German market data and AI media tools.
