AI connector

An AI connector is a capability for querying a metadata catalog in plain language. The model reads the description of the estate rather than the files, so a question can be asked without the contents entering the conversation.

Key takeaways

An AI connector lets people query a metadata catalog in plain language.
Teams ask questions in plain language instead of building queries.
Model Context Protocol (MCP) is an open standard for connecting AI assistants to tools.

Why connect AI to a metadata catalog?

So people can ask questions about their data in plain language, and get answers based on facts. A storage administrator can ask which projects are the largest, or which grew the most over the period covered by the indexes the organization keeps, instead of building a query. Because the AI works from the catalog, its answers come from recorded metadata rather than guesses, and every recommendation it makes still waits for a person to approve it.

Can an AI assistant query a metadata catalog directly?

Yes. Diskover’s AI connector lets a model query the catalog in plain language and get matching files back with a recommended action for a person to approve. The model reads the description of the estate rather than the files themselves, which keeps the contents out of the conversation.

Can AI read and catalog metadata?

Reading metadata is mechanical work. A crawler asks the file system for each file’s attributes, one call at a time, and writes them to an index, a job that was solved long before current models existed. A model earns its place afterward: interpreting what the attributes imply, proposing a class for a group of files, and letting someone ask the index a question in plain language rather than building a query. The reading stays mechanical. The asking becomes conversational.

What is Model Context Protocol (MCP)?

Model Context Protocol, or MCP, is an open standard that lets AI assistants connect to outside tools and data sources in a consistent way. Instead of a custom integration for each tool, an application describes what it can do through MCP, and any compatible assistant can use it. For file data, this means an assistant can ask a catalog questions in plain language and get structured answers back.

Can the AI connector move or delete files?

No. The AI connector can recommend actions, such as moving or deleting a set of files, and it can apply tags only after a person approves them. Nothing changes until someone says yes. It works from metadata only and never reads file contents.