immo-mcp
Provides geocoding and points of interest search via Nominatim and Overpass API.
Click on "Install 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., "@immo-mcpWhat is the median price per m² in Bordeaux?"
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.
immo-mcp
An MCP (Model Context Protocol) server for French real-estate market analysis, built exclusively on open data sources. No third-party site automation.
Data sources
Source | What it provides |
All notarised property transactions in France (2018-present) | |
Same DVF data, queryable without a local DB | |
Energy-performance certificates (DPE) | |
Flood, seismic, radon, ICPE risk data | |
Regulated electricity tariffs | |
Postal code → INSEE commune lookup | |
Geocoding and points of interest |
Related MCP server: Property Comparable Sales MCP Server
MCP tools
Tool | Description |
| Search DVF transactions by city / postal code / department |
| Aggregate price statistics from DVF (median, p25/p75, …) |
| Report on the local DuckDB DVF database |
| DVF statistics via the OpenDataSoft public API |
| Compare a market segment against DVF + ODS reference prices |
| Search DPE certificates by city or postal code |
| Risk analysis for a location (flood, seismic, radon, ICPE) |
| List available Géorisques risk categories |
| Fetch current regulated electricity tariffs (CRE) |
| Resolve a postal code to its INSEE commune codes |
| Forward geocode an address via Nominatim |
| Search points of interest around a location (OSM Overpass) |
| List available POI category presets |
| Compute price statistics on a list of listings |
| Annotate listings with gap-from-median percentage |
Quick start
1. Install
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt2. (Optional) Build a local DVF database
For faster, offline DVF queries you can build a local DuckDB:
# Requires Docker
cd docker/dvf
DVF_HOST_DATA_DIR=~/.immo-mcp/dvf docker compose upThe MCP server will look for the database at ~/.immo-mcp/dvf/dvf.duckdb.
Without it, the dvf tool falls back to the OpenDataSoft API automatically.
3. Start the server
python -m immo_mcp.server4. Connect from Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"immo-mcp": {
"command": "/path/to/.venv/bin/python",
"args": ["-m", "immo_mcp.server"]
}
}
}Environment variables
Variable | Default | Description |
|
| Path to local DuckDB DVF file |
|
| SQLite listing cache |
Development
pip install -r requirements.txt
pytestLicense
MIT — see LICENSE.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/WardenPro/immo-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server