Semcore MCP Server

The semantic core reachable from the assistant already in your editor, without leaving it to find out what a table or a metric means.

Governed definitions are used in the tool engineers already live in, rather than consulted somewhere else.

The tools an assistant calls to read your semantic core: what a table means, where it is bound, what it draws on, and what a change to it would have to pass. They answer from the definitions your organisation has agreed, so the assistant is reading your business rather than guessing at it from schemas.

It works with MCP compatible clients, so the assistant you already work in is the one that reads your definitions.

  • search_catalog_tables

    Find the tables in your catalog that match what you are looking for.

  • get_catalog_table_context

    Read what a table means, in the terms your business uses for it.

  • get_engine_bindings

    Find where a table is bound in the engines your estate runs.

  • get_lineage

    Trace what a table draws on, and what draws on it.

  • propose_gold_model

    Put a model of a business concept forward for a decision.

  • propose_semantic

    Put a definition of a metric or a dimension forward for a decision.

  • validate_catalog_table

    Check a table against the rules a definition has to meet.

  • list_proposals

    See what has been put forward.

Start with what you already have

An AI Readiness Review

A scoping conversation, and a look at your data estate as it stands: what your AI plans will need from it, where the gaps are, and which of them to close first. The findings are yours either way.