Frequently Asked Questions (FAQ) about the MCP Server for Enterprise Search (France)

Q: What is an MCP Server?

A: An MCP (Model Context Protocol) Server acts as a bridge, allowing AI models to access and interact with external data sources and tools. It provides a standardized interface for data retrieval, making it easier for AI Agents to gather the information they need.

Q: What is the UBOS Asset Marketplace?

A: The UBOS Asset Marketplace is a curated collection of pre-built components, including MCP Servers, that simplify the development and deployment of AI Agents on the UBOS platform.

Q: What data does this MCP Server provide access to?

A: This MCP Server provides access to the French enterprise search API made available by data.gouv.fr. This includes data on French companies, such as their official name, SIREN/SIRET numbers, NAF codes, and address.

Q: What type of searches can I perform with this MCP Server?

A: You can perform textual searches based on company name, address, and the names of directors/elected officials. You can also perform geographic searches within a specified radius of a given location.

Q: What are the limitations of the data provided by this MCP Server?

A: The data provided by the data.gouv.fr API does not include access to predecessor/successor information, non-public companies, or companies denied registration. The geographic search radius is limited to 50km.

Q: How do I use this MCP Server?

A: You can use it via npx with the command npx mcp-recherche-entreprises. As a developer, you can install the dependencies, build the project, and start the server. Detailed instructions are provided in the “Getting Started” section above.

Q: Can I use this MCP Server with Cursor?

A: Yes, you can easily integrate this MCP Server with Cursor by adding a simple configuration to your .cursor/settings.json file.

Q: What is UBOS?

A: UBOS is a full-stack AI Agent development platform designed to orchestrate AI Agents, connect them with enterprise data, and build custom AI Agents with your own LLM model and Multi-Agent Systems.

Q: What are the technical limitations of the API?

A: The API has a limit of 7 calls per second and has been available 100% of the time over the last month. Access is open to everyone.