$ loading_
Ground dataset questions with schema, lineage, and trust signals.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Context Catalog MCP" yet — see the docs or source repo.
Inspect the sales.orders table: list fields, types, and primary key, and explain the structure.
Returns a schema summary to help quickly understand the fields.
Trace the lineage for this metric’s dataset and list upstream sources.
Returns lineage paths and upstream dependencies.
Check the data-quality trust signals for the customers table and tell me whether it is suitable for analysis.
Returns quality and trust signals to judge whether the data is usable.
A data analyst can verify schema, field meaning, and source lineage before reporting or modeling. The tool pulls grounded catalog information to reduce mistakes.
Developers or researchers can use it to answer questions like where a table comes from, what upstream dependencies it has, and whether it is trustworthy.
When an AI agent needs to answer from catalog data, this MCP tool provides schema, lineage, and quality signals to reduce hallucinations.
It is an MCP tool that exposes schema, lineage, and data-quality trust signals from a SQLite-backed catalog. It helps AI agents answer dataset questions using grounded catalog data.
It can help query dataset structure, fields, lineage, and quality/trust signals. For any more specific capabilities, see the source repository.
It does not invent answers; it retrieves traceable information from the catalog. This makes it better suited for grounded data workflows.
Provide LLMs a governed data layer for SQL, metrics, lineage, and catalog.
Safely query SQLite databases and preview schemas through a standardized MCP interface
Connect AI to SQLite and query tables using natural language.
Enable AI to safely analyze business metrics without improvising raw SQL.
Ask research questions on real datasets and get actual database records back.
Inspect database schemas, index issues, table bloat, and query plans.