What kind of shop types are available?

The MCP supports 28 different classes, including supermarkets, bakeries, electronics, pharmacies, and more.

How is the restaurant data filtered?

You can filter restaurants by cuisine type, whether they are open now, and their proximity to you.

Can I find specific shopping malls?

Yes, the find_malls capability allows you to search for shopping centers by name or proximity.

Does this include contact information?

Yes, many capabilities return phone numbers and opening hours for the businesses found.

How accurate are the brand rankings?

The top_shop_brands capability uses a 500-shop sample to rank the most frequently mapped retail chains.

Do I need an API key?

No. Every source is keyless and global: OpenStreetMap (Overpass + Nominatim), Open-Meteo and Russian Wikipedia. The MCP defines no credentials.

Why does a chain appear more than once under different names?

The map records brand tags as mappers wrote them (Пятёрочка, Pyaterochka, 5ka). top_shop_brands shows the variants ranked by frequency. pick the exact value for find_shops.

Why are the counts bigger than the listed rows?

Yes. OSM maps most large venues as areas (buildings, park outlines), and every capability uses the nwr selector, so nodes, ways and relations all count. Point-only queries would miss them.

Can I find shops near me?

Pass lat + lon (and optionally km, 0.1–25) and the query narrows to a radius instead of the whole city. Use it before a long list. a citywide scan is heavy and capped at 200 rows.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Moscow Shops Malls Restaurants to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Get real-time retail and dining data for Moscow.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through OpenStreetMap (Overpass).

01
Find malls
Find shopping centers in Moscow. It returns the name, operator, and coordinates for about 120 malls like Vavilon.
02
Find markets
Locate food and street markets. You can filter by name or check if they are currently open.
03
Find restaurants
Search for restaurants, cafes, or fast food. It provides cuisine types, phone numbers, and delivery availability.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through OpenStreetMap (Overpass).

04
Find shops
Query 28 different shop classes including supermarkets, pharmacies, and clothing stores. It includes brand names and real-time opening status.
05
Shopping category counts
Get citywide totals for nine different retail and food categories to understand market density.
06
Top shop brands
Identify the most frequent retail chains in Moscow. Use this to find the exact brand names used in the database.

Real work

What teams actually run

Local Dining

Ask your agent to find a specific type of cuisine that is open late in your current neighborhood.

Retail Research

Determine which supermarket chains have the highest presence in the city.

Daily Errands

Locate the nearest pharmacy or grocery store that is currently open.

Market Analysis

Get a count of different food and retail categories to understand citywide distribution.

One connector, every AI

OpenStreetMap (Overpass) works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put OpenStreetMap (Overpass) to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

917ms average. Fast in production.

OpenStreetMap (Overpass) is checked daily against the live service.

Daily averagePeak 1106ms

Oct 3Today

Fastest day: 712ms
Slowest day: 1106ms
14-day trend: Improving-5%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of OpenStreetMap (Overpass), so you can see the experience inside your AI.

It does not authenticate your account with OpenStreetMap (Overpass). Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

OpenStreetMap (Overpass) Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_KY2FzJrqOqbKvQmilh02ySJcVyOtjqKYErdFroRL/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — OpenStreetMap (Overpass) capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "moscow-shops-malls-restaurants-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_KY2FzJrqOqbKvQmilh02ySJcVyOtjqKYErdFroRL/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up OpenStreetMap (Overpass) in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work OpenStreetMap (Overpass) owners hand off.

This MCP is built for anyone needing precise, real-time location data for Moscow's commercial sectors.

01
Developers
Building location-aware agents that need reliable Moscow retail data.
02
Data Analysts
Querying retail density and brand presence within the city.
03
Travelers
Using an AI client to find immediate dining or shopping options.

FAQ

Questions OpenStreetMap (Overpass) owners ask.

01
What kind of shop types are available?
The MCP supports 28 different classes, including supermarkets, bakeries, electronics, pharmacies, and more.
02
How is the restaurant data filtered?
You can filter restaurants by cuisine type, whether they are open now, and their proximity to you.
03
Can I find specific shopping malls?
Yes, the find_malls capability allows you to search for shopping centers by name or proximity.
04
Does this include contact information?
Yes, many capabilities return phone numbers and opening hours for the businesses found.
05
How accurate are the brand rankings?
The top_shop_brands capability uses a 500-shop sample to rank the most frequently mapped retail chains.
06
Do I need an API key?
No. Every source is keyless and global: OpenStreetMap (Overpass + Nominatim), Open-Meteo and Russian Wikipedia. The MCP defines no credentials.
07
Why does a chain appear more than once under different names?
The map records brand tags as mappers wrote them (Пятёрочка, Pyaterochka, 5ka). top_shop_brands shows the variants ranked by frequency. pick the exact value for find_shops.
08
Why are the counts bigger than the listed rows?
Yes. OSM maps most large venues as areas (buildings, park outlines), and every capability uses the nwr selector, so nodes, ways and relations all count. Point-only queries would miss them.
09
Can I find shops near me?
Pass lat + lon (and optionally km, 0.1–25) and the query narrows to a radius instead of the whole city. Use it before a long list. a citywide scan is heavy and capped at 200 rows.

Explore

More in Food Beverage

Connect OpenStreetMap (Overpass) to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-03

Find malls

Find markets

Find restaurants

04-06

Find shops

Shopping category counts

Top shop brands

What teams actually run

Local Dining

Retail Research

Daily Errands

Market Analysis

Building your own app? The connector is yours to use.

OpenStreetMap (Overpass) Connector

Claude Desktop

Developers

Data Analysts

Travelers

What kind of shop types are available?

How is the restaurant data filtered?

Can I find specific shopping malls?

Does this include contact information?

How accurate are the brand rankings?

Do I need an API key?

Why does a chain appear more than once under different names?

Why are the counts bigger than the listed rows?

Can I find shops near me?

Marketplacer (Enterprise Marketplace Platform) AI Connector

Moscow Schools, Kindergartens & Universities AI Connector

European Market Opportunity Analyzer AI Connector

Moscow Museums, Theatres & Libraries AI Connector

Suggestions

Moscow Places & Geography AI Connector

Moscow History, Heritage & High-Rises AI Connector

Moscow Hotels, Hostels & Stays AI Connector

Moscow Transit: Metro, Rail, Bus & Parking AI Connector