
Yatmo neighbourhood data for real estate
com.yatmov1.0.0Updated Oct 2, 2026
Real estate neighbourhood data: nearest school, shops, transport with travel times, 25 countries.
Overview
Gives an assistant Yatmo neighbourhood data for a property location: nearest school, nursery, supermarket, transport and travel times in 25 countries.
- What it does
- Yatmo is a remote MCP server exposing four tools that take latitude, longitude, country and language. yatmo_get_location_summary returns a quotable neighbourhood paragraph plus the nearest school, nursery, supermarket, transport and reverse-geocoded place; yatmo_get_nearby_pois lists points of interest within a radius, optionally filtered by category; yatmo_get_nearest_by_category returns the single nearest place of a category with distance and travel time; yatmo_get_accessibility_profile reports public-transport presence, nearest stop, train station and motorway access. Every tool returns the same envelope of text, facts, warnings and metadata.
- When to use it
- Useful when an assistant has to answer what is around a property, for example for real estate listings, relocation questions or accessibility checks. It suits agents that need structured nearby-place facts and a ready-to-quote summary rather than raw map data.
- Requirements
- A remote Streamable HTTP endpoint at nothing runs locally. A Yatmo backend licence key is required, sent in the LicenceKey header (LicenseKey also accepted); OAuth 2.1 with a consent page is supported for clients that prefer it. Keys come from yatmo.com, and Yatmo is a paid service.
Installation
In SourceWeft
- Open Yatmo neighbourhood data for real estate in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"yatmo": {
"type": "http",
"url": "https://mcp.yatmo.com/mcp/v1"
}
}
}README
Yatmo MCP server: neighbourhood data for AI assistants and agents
Yatmo exposes its neighbourhood intelligence to AI clients through a remote MCP server. Connect Claude, Cursor, VS Code or your own agent, and it can answer "what is around this property?" with real data: nearest school, nursery, supermarket, public transport, train station, motorway access, distances with travel times, and a quotable summary paragraph, in 25 countries.
This repository holds ready-to-copy client configurations and a dependency-free quick start. The server itself is
operated by Yatmo at https://mcp.yatmo.com/mcp/v1 (Streamable HTTP). Full documentation:
documentation.yatmo.com/mcp.
The four tools
All tools take latitude, longitude, country (BE, FR, UK...) and language, and return the same envelope:
text (a summary the assistant can quote), facts (structured data), warnings and metadata. Categories use one
vocabulary everywhere: school, nursery, supermarket, public_transport, train_station, motorway.
Details: tools reference.
Authentication
Every request carries your Yatmo backend key in the LicenceKey header (LicenseKey is accepted too). Keep the
key in the client's secret store, never in a public web page: the key grants access to your Yatmo account. Get a key at
yatmo.com; keys explained.
Connect a client
Generic remote-MCP configuration (configs/mcp.json), accepted by most clients, sometimes under a slightly different parent key:
Claude.ai and Claude Desktop: Settings > Connectors > Add custom connector, URL https://mcp.yatmo.com/mcp/v1,
custom header LicenceKey: YOUR_KEY. The four tools appear once the connector is enabled.
Claude Code:
Cursor: copy configs/cursor/mcp.json to .cursor/mcp.json in your project (or to
~/.cursor/mcp.json for every project).
VS Code (Copilot agent mode): copy configs/vscode/mcp.json to .vscode/mcp.json.
Your own agent (Anthropic, OpenAI or any LLM SDK): use an MCP client library (TypeScript, Python, .NET, Go) with the
Streamable HTTP transport, add the LicenceKey header to the transport, and forward the four tool definitions to the
model. quickstart.py shows the raw protocol without any library.
Try it from the command line
Prompts that work well
- "What is the neighbourhood like around 50.8467, 4.3525 in Belgium? Answer in French."
- "Nearest primary school and supermarket to this listing, with travel times on foot."
- "Is this address well served by public transport? Nearest train station and motorway access?"
- "List the points of interest within 800 m of the property, schools and supermarkets only."
The assistant answers from the text and facts of the tools; distances come with the mode they were measured in.
More
- Quick start, authentication and error codes, FAQ
- The same data for websites: plugins, WordPress, Odoo, mobile SDKs, examples
MIT licence for the files of this repository. Yatmo is a paid service for real estate portals, agency networks and developers.
Directories
The server is published in the official MCP registry as com.yatmo/yatmo (server.json in this repository) and submitted to the Docker MCP Catalog, Smithery and mcp.so. In clients that read the registry, search for "yatmo" or "real estate".
Source: README.md at commit d7aed91
Tools
0Version history
1- v1.0.0LatestOct 2, 2026
