Paris Compass MCP

Compass

Before you sign a lease, read the street.

*What traded at this address, how the street turns over, what goodwill sold for. Public sources only, every figure cited.*

[Open the demo →](https://paris-compass.lovable.app) · no account needed · pre-recorded addresses, 17th arrondissement

For an agent → npx -y paris-compass-mcp · six tools, read-only, on the hosted corpus

The question

You are standing in front of an empty shopfront. The agent says the street is lively.

Compass answers on six axes at once.

Each of those arrives with its source, its date and its confidence level.

Note the wording, because the product keeps it too: air quality is *measured*, noise is *modelled*. Noise and footfall are proxies, labelled as such on screen and here.

Three that deserve more than a line

Has a kitchen ever been here? If a restaurant occupied the unit, the extraction, grease trap and power are probably already in. If not, creating them runs into tens of thousands and needs the building's agreement. The most expensive question this data answers — before you travel.

Is this a graveyard or a good street? A street that churns is not a street that dies: units can turn over and refill. And turnover only means something against its own trade, and against its own quartier — the same trade does not hold equally from one neighbourhood to the next. Compass measures both across three censuses.

Those figures are not printed here. They rest on the 2017 and 2020 vintages, whose licence has not been cleared, and the server withholds them from an anonymous caller. This page follows the same rule as the product: a rate derived from a withheld vintage is withheld too.

What did people actually pay? 25 661 goodwill sales published with their price since 2015. For the 5 971 tied to a single shopfront, the median Paris *fonds* changes hands between 160 000 and 170 000 € — a range, not a point, because goodwill prices are declared in round numbers: the median sits on a step and moves in jumps, so a single figure would be precise about something the source is not. The trade decides almost everything.

One address makes the point. At 10 rue Mandar, trace_premise returns six goodwill sales between 2017 and 2024, from 87 500 to 450 000 € — retrieved 7 October 2026. Each one is probable, not established: two shopfronts share that street number, and the notice does not say which was sold. The 2017 and 2020 census rows come back withheld, the 2023 one established.

How a number earns its place

Every figure arrives with its source, its licence, its date — and how sure it is.

flowchart LR

A["APUR BDCom 3 censuses"] --> M["Address matching"] B["BODACC sales + insolvencies"] --> M C["INSEE Sirene establishments"] --> M M --> V{"Does the source name THIS unit?"} V -->|"names it directly"| E["established"] V -->|"two sources agree, neither names it"| F["corroborated"] V -->|"address shared by several shopfronts"| G["probable"] V -->|"source is silent"| H["undetermined"] E --> O["Every figure carries source · licence · vintage · method"] F --> O G --> O H --> O O --> UI["Map and unit file"] O --> MCP["MCP server, for an agent"]

Four levels, never a percentage. A confidence score out of 100 would be exactly the kind of unverifiable number this product refuses. The level is *computed* from columns that already exist, and every row carries the reason that produced it.

Composition across the corpus, measured 6 October 2026 — this is the quality metric, and improving means moving these four numbers leftward:

That 37.0% is structural, not laziness: BODACC names an *address*, BDCom names a *unit*, and 69% of units share their street number. No public data will say which of eight shopfronts was sold.

A gate runs the whole corpus against 56 invariants, 24 frozen baselines and 8 hand-verified chronologies before anything ships, and again every day on a schedule — invariants counted 6 October 2026 with grep -c '^-- @invariant ' eval/invariants.sql. Most of them check what the functions return; one checks what they *are* — a function exposing an observed column must be SECURITY DEFINER, because row-level security silently turns a withheld row into "never surveyed".

The badge above counts invariants; it does not say the gate passes. The reds currently open are the issues labelled porte-rouge.

Two founding constraints

Most commercial-property tools describe the unit — floor area, rent, photos — and leave you to infer the rest. Compass sells neither coverage nor granularity: it sells interpretation, and context is the product.

An interpretation is worth only what you can check. The tools in this market promise answers *grounded in audited data* — that names who verified. Compass promises figures re-derivable from a cited public source — that names who *can* verify: you. An internal audit is a promise. A cited source is a test anyone can rerun, including against us.

If a number cannot be re-derived from a cited public source, it is not shown.

No landlord declarations, no scraped listings, no proprietary estimate, no score invented to fill a gap. Missing data is displayed as missing — n/a, never 0.

If two units on the same street get the same verdict, Compass has said nothing.

The useful granularity is the street segment, sometimes the side of the pavement. An indicator that does not vary at that scale describes general context; it does not settle a decision.

Who it is for

The entrepreneur — the shopkeeper, restaurateur, craftsperson or franchisee who decides *where* to open. Once or twice in a working life, on a lease that binds for years.

An agent — an LLM asking the same question through an MCP server. Same scoring core, same traceability requirement, different output: JSON and a chain of thought instead of a map.

Not brokers. A broker qualifies dozens of locations a month and needs portfolios, bulk comparison, national coverage. Every one of those makes the product heavier for someone studying a single address in depth. Serving both serves neither — a broker who wants Compass gets what the agent gets: the API.

What it refuses

Every refusal buys something back. The trade is the point.

What it cannot answer, and why — the gaps shape the product more than the features do

What rent will I pay? No open observatory of commercial rents exists in France. Local rent observatories cover private *housing*; INSEE's ILC is a revision index, not a level. Street-level commercial values are sold by private vendors — which is the proof they are not open. Goodwill sale prices carry an indirect signal and nothing more.

How many people walk past this door? Paris has no permanent pedestrian sensor: the city's multimodal counters cover bikes, scooters, motorcycles, cars, lorries and buses — not pedestrians.

Vendors do sell the number, and "proprietary and expensive" is the weak objection — worth being precise about what it actually is. It comes from a panel of mobile handsets: SDKs embedded in third-party apps report GPS coordinates in the background, and the sample is then extrapolated by weighting it against known demographics. The vendors say so themselves — *"We don't see everyone. We see a sample."* Peer-reviewed work on a comparable panel measured a mean sampling rate of 7.5%, swinging between 4.5% and 14.5%, with low-income and less-educated populations under-represented and the urban/rural bias reversing sign mid-series. 1

So the figure is modelled, never measured — and the buyer cannot see the panel size on their own street, cannot replay the weighting, and is not told when a recalibration moves last year's number. The objection is not honesty, it is verifiability. Compass measures *presence and rhythm* from open sources instead, and labels it a proxy on screen.

1 Li Z., Ning H., Jing F., Lessani M. N. (2024). *Understanding the bias of mobile location data across spatial scales and over time.* PLOS ONE 19(1):e0294430.

What do people here spend, and on what? Card transaction data: proprietary. No workaround.

Which units are on the market today? Commercial listings live on private portals whose terms forbid reuse. Which is why Compass works upstream of them instead.

Status

Honest labels, in the sense that *built* means the code runs and the gate passes — not that it is deployed.

| Deployed to the hosted da