France Data MCP
Related Servers
Alternatives to France Data MCP
- AlicenseAqualityNot gradedmaintenanceUnified API for Government Data and Web Scraping100-
Related Servers
- FlicenseNot gradedqualityCmaintenanceProvides AI agents with access to French public registries including company records, property sale prices, housing energy performance, and short-term rental rates via MCP tools.-
- AlicenseAqualityCmaintenanceA French administration MCP server that enables AI agents to access official public data including communes, geocoding, property risks, and energy performance certificates (DPE) for real estate evaluation.4MIT
- AlicenseAqualityAmaintenanceAn MCP server that connects AI chatbots directly to data.gouv.fr, France’s national open data platform. It allows users to search, explore, and analyze thousands of public datasets simply by asking questions in natural language.101,597MIT
- AlicenseNot gradedqualityBmaintenanceA hosted MCP server for French address data quality, geocoding, and routing, allowing LLMs to verify, normalize, search addresses, and compute routes using official open data sources.3MIT
- AlicenseNot gradedqualityFmaintenanceEnables AI assistants to search and retrieve French legislation, case law, and EU law integrations from official sources via MCP.115 npm1Apache 2.0
- AlicenseAqualityBmaintenanceExposes French and EU public procurement data (BOAMP + TED) as MCP tools for AI agents, enabling search for tenders, awards, and winner intelligence via typed filters.459 PyPIMIT
TDQS
Scored across 37 tools
Most tools have clearly distinct purposes, but some pairs could be confused: e.g., `professionnels_in_radius` vs `professionnels_rpps_in_radius` (libéraux vs all statuses), and `etablissements_finess_in_radius` vs `centres_sante_in_radius` (which is a subset). However, detailed descriptions mitigate ambiguity.
Names mix French and English conventions, with patterns like `_in_radius`, `_by_`, `_par_`, and verbs in both languages. While there is some consistency (e.g., `_in_radius` for spatial searches), deviations like `by_categorie` vs `par_` and `get_commune_by_code` vs `autocomplete_commune` make it less predictable.
At 37 tools, the server exceeds typical expectations. While it covers a broad domain (health, demographics, real estate), the sheer number may overwhelm agents, warranting more aggregation or segmentation. The high count increases selection complexity.
The tool surface is remarkably comprehensive for French territorial health data: it covers establishment and professional lookups, spatial and administrative enumeration, density, demographics, real estate, data freshness, and aggregations. Minor gaps include lack of direct health insurance rate data, but the core workflows are fully supported.