mcp · Global

paris-compass

A contextual commercial real estate search application for Paris that puts any space back into its environment (walkability, retail, transport, schools, healthcare, parks, noise, air quality, risks, ...,) using public open data.

Visit source ↗GitHub repository ↗

Feature or claim this listing

Feature this listing — founding Featured slots are 50% off for 6 months

Represent paris-compass? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Explore paid sponsorship →

What's in it

Data offered docs-verified: goodwill (fonds de commerce) sale prices, Paris · BDCom commercial unit census 2017 / 2020 / 2023 · BODACC sales and insolvency notices · INSEE Sirene establishments · air quality: AQI, PM2.5, NO2 (CAMS via Open-Meteo) · natural and technological risks within 1 km (Géorisques) · amenities (schools, healthcare, food, parks, transit) and walkability · road noise (modelled, proxy) · rent control dataset (housing only)
Coverage docs-verified: Paris intra-muros · goodwill sales since 2015; BDCom censuses 2017, 2020, 2023
Resolution docs-verified: Premises matched per unit / street number; amenities counted within 800 m, risks within 1 km, road noise modelled from roads at 500 m
Formats docs-verified: JSON · MCP
Access docs-verified: Free, anonymous read-only MCP server (npx -y paris-compass-mcp), nothing to configure per docs; code licence Apache-2.0. Entry metadata separately lists an API key (VITE_SUPABASE_PUBLISHABLE_KEY) for the web app.

Useful for

Use cases llm-inferred: Pre-lease due diligence on a Paris shopfront: prior trades and goodwill price range for a street number · Street-level premise turnover and insolvency screening before taking on a commercial unit in Paris · Environmental context screening for a Paris site: air quality and Géorisques risks within 1 km
Audience llm-inferred: entrepreneurs and retail tenants choosing a commercial unit · LLM agents querying via MCP · planners and environmental screening consultants working in Paris

Limitations

Constraints llm-inferred: Paris intra-muros only; not UK coverage · 2017 and 2020 census vintages withheld for anonymous callers (licence not cleared) · Many premise matches are 'probable' rather than confirmed (about 37% of corpus) because several shopfronts share a street number · Noise and footfall are modelled proxies, not measurements · No open commercial rent data; rent figures are not provided · Hosted corpus live since 15 August 2026; web demo uses pre-recorded addresses only · Some gate checks are failing (open 'porte-rouge' issues) · Entry tools list is empty and auth metadata conflicts with the anonymous-access claim · Built and maintained by a single public project; maintenance risk

Licence: Apache-2.0
Authentication: API key via env: VITE_SUPABASE_PUBLISHABLE_KEY (auto-extracted from README)
GitHub stars: 1
Last commit: 14/10/2026
Last successful page check: 14/10/2026
Page health: healthy
Package: Not recorded
Verification: Not independently verified

Auto-extracted, unverified fields: tools, auth. Check upstream documentation.

Provenance & evidence

Daily discovery 2026-10-15: GitHub search; verified via GitHub API. Tools/install/auth auto-extracted from README.

Metadata observed 16/10/2026 · daily-2026-10-15 (github-search)