Normi API & MCP
French property data, native to your agents.
33 MCP tools and a REST API over the same data: 18.8M real sales, 23.8M ADEME energy ratings (DPE), 32.4M BDNB buildings and the SIRENE business register. 500 free credits, no card.
MCP · RESTSTDIO · HTTP Streamable · OAuth2014–2026
Integrations
Works with your AI tools
One-click OAuth sign-in, local STDIO or HTTP Streamable — set up Normi in 2 minutes
Agent-native
Built to be called by agents
Stateless MCP
No server-side session: every request stands on its own. A redeploy is invisible to connected clients.
Two protocol revisions
The 2026-07-28 MCP revision and 2025-era clients are served by the same endpoint, request by request.
Revocable connector URL
For ChatGPT and Claude: a dedicated HTTPS URL you can revoke at any time from your dashboard.
In the official MCP Registry
Published as io.github.NormiHQ/normi, with the @normi/mcp-dvf npm package for local clients.
The join
The only commercial API that joins DPE ratings to DVF sales.
14.2M sales are linked to the nearest ADEME diagnosis within 200 m. Green premium, share of energy sieves and the price gap by energy class are computed commune by commune.
How the join is builtDVF Tools
33 MCP tools
Search, statistics, estimations, market score, DPE energy diagnostics, BDNB buildings, portfolio and webhook alerts.
DVF sales
search_property_transactions
5cSearch French property transactions with location, price, surface, date, property type filters and auto-dedup.
analyze_market_statistics
5cMarket statistics: median, average, price per m², surface areas and transaction volume in an area.
find_property_comparables
10cSelection of comparable properties with similarity score and value estimation.
estimate_property_value
10cAutomated valuation (AVM): low/median/high price range from real DVF comparables.
lookup_property_history
20cTransaction history for an address with price evolution and associated transactions.
Market analysis
analyze_price_trends
10cTime series (month/quarter/year) with trends and YoY changes.
score_market_health
10cMarket health score (0–100) based on volume, price trend and price dispersion.
compare_locations
10cComparison of 2 to 5 neighborhoods with multi-criteria rankings.
analyze_market_activity
10cMarket activity index (hot/normal/slow) by zone and period.
analyze_rental_yield
10cEstimated gross rental yield: ANIL rents cross-referenced with DVF prices by commune.
get_property_risk_signals
10cGéorisques geographic risk signals for a point: clay, radon, seismic zone, GASPAR procedures.
get_zonal_price_distribution
15cPrice statistics by zone (postal code / commune) with GPS centroid — JSON data for map visualizations.
analyze_purchasing_power
5cPrice-to-income ratio (DVF × INSEE Filosofi) to measure an area's real estate purchasing power.
detect_flips
10cDetects short-hold resales (18–24 months) and their markup by commune.
get_market_overview
10cComposite market brief: stats, trend and health in one call, replaces 3 requests.
Energy (DPE)
Buildings (BDNB)
get_building_characteristics
2cBDNB building closest to a DVF transaction: construction year, wall materials, usage, number of floors.
analyze_building_age_price_impact
10cMedian DVF price/m² by construction era (pre-1919, 1919–1945 … 2006+) with deviation from zone median.
score_renovation_potential
10cRenovation potential score (0–100): old buildings priced below the local market median.
analyze_building_stock
5cCSTB building stock for a commune or department: breakdown by era, usage and number of residential units.
Portfolio and alerts
add_property_to_portfolio
10cAdd a property to the portfolio and automatically compute its DVF estimate.
list_portfolio_properties
0cList all portfolio properties with their current DVF estimates.
get_portfolio_property
0cRetrieve a portfolio property by ID with its current DVF estimate.
update_portfolio_property
0cUpdate the characteristics of a portfolio property.
delete_portfolio_property
0cRemove a property from the portfolio.
create_market_alert
0cCreate a webhook alert triggered on new matching DVF transactions.
list_market_alerts
0cList all active DVF alerts for the account.
update_market_alert
0cUpdate the criteria of an existing alert (area, price, property type).
delete_market_alert
0cDelete a DVF alert.
Quick Installation
3 steps to get started
Free token, JSON config, first DVF query.
- 01
1. Get a token
Generate a free token (normi_xxx) on the get-token page. Used in NORMI_API_KEY (STDIO) or Authorization Bearer (HTTP).
- 02
2. Configure your MCP client
STDIO for local clients (Claude Desktop). HTTP streamable for Cline/Cursor/VSCode and your backends (Authorization Bearer).
- 03
3. Test a DVF query
Ask: Find apartments sold between 2023 and 2024 in Lyon between 200k and 400k.
- One click from the Claude connector directory
- claude.ai, Claude Desktop, mobile and Cowork
- Revocable from the dashboard (Connected apps)
// Claude connector directory: https://claude.ai/directory/normi // Add → sign in to Normi → Authorize // No key to copy // Without the directory: custom connector https://mcp.normi.fr/mcp
Three guided prompts are included so you can explore the data without reading the docs. See the MCP prompts
AI Assistants
Ask your AI assistant about French property prices
Normi is indexed by Claude, ChatGPT, Perplexity and all major AI crawlers. Whether you are researching French real estate or building an AI agent, Normi provides authoritative DVF data your AI can cite.
Claude Desktop / Code
MCPInstall the MCP server once, then ask Claude directly: "What is the median price per m² in Lyon 3rd arrondissement?"
ChatGPT
MCPConnect Normi directly to ChatGPT via a revocable MCP URL — no raw API token needed. Generate the URL from the dashboard.
Custom AI agents
REST APIUse the REST API to embed live DVF data in your own agent pipelines. OpenAI, Anthropic, Mistral — any LLM that can call HTTP.
Pay per call, in credits
Every tool shows its cost. 500 free credits every month, then credit packs or an API plan as your volume grows.