"Elm" matching MCP servers:

Enables the analysis of massive datasets by storing data in external variables via a sandboxed Python REPL instead of the model's context window. This allows users to process files larger than 100MB without polluting the context or hitting token limits.

Provides LLM clients with OAuth-authenticated, organization-scoped access to a dbt knowledge base, enabling browsing, semantic search, and retrieval of model details such as SQL, lineage, and project structure.