Model Context Protocol (MCP) server that gives AI assistants a safe, correct data-analyst capability over business metrics - without raw SQL improvisation.
A local-first MCP server that provides safe, governed read-only SQL access to SQLite and PostgreSQL, with validation, limits, task tracking, and report generation.
MCP server for the OrionBelt Semantic Layer. Enables LLMs to explore governed semantic models, compile YAML metric definitions into optimized SQL across 8 engines (BigQuery, ClickHouse, Databricks, Dremio, DuckDB, MySQL, PostgreSQL, Snowflake), and execute analytics queries via natural language. Works with Claude, Cursor, Windsurf, and Copilot.
Read-only MCP server for SQL databases (SQL Server, Postgres, SQLite) with multi-server support and three-layer safety using AST validation and linting.
This MCP server gives AI assistants over business data a provenance layer: every number in an answer traces back to specific records, auditable and tamper-evident. It enforces that the model never generates figures—only selects operations whose results are computed deterministically in SQL.