Builds a metadata and lineage graph from dbt artifacts, enabling lineage-aware analysis and querying over dbt project metadata.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Warehouse Graph MCP Server which upstream dbt models feed the orders fact table?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Shared foundation for two linked projects:
warehouse-qa: a governed, lineage-aware "ask your warehouse" assistant
pipeline-sentinel: a tiered incident agent for data pipelines
This package will build a metadata/lineage graph from dbt artifacts, compile one policies.yml to database access controls (Postgres RLS / Unity Catalog), and serve the graph over an MCP server.
Status: Phase 0 (setup). So far: repo tooling, local Postgres, and the LLM wrapper that every model call goes through (response cache, cost ledger, hard budget cap, Batch API rounds, prompt caching).
cp .env.example .env # add ANTHROPIC_API_KEY for real model calls
uv sync
make up # Postgres 16 via Docker Compose
make check # lint, format check, type-check, tests
make llm-smoke # one cheap real call; logs a row to costs.csvRelated MCP server: dagsmith
docs/design-decisions.md: decisions and why
docs/parking-lot.md: ideas deliberately left out of v1
MIT
This server cannot be deployed
The grounded data layer for any LLM: governed SQL, metrics, lineage and catalog over your data.
Define, ship & query your analytics tracking from one source of truth, trusted by humans and agents.
Cross-tool context for your data stack. Search, lineage, and impact across warehouse and BI tools.
Provenance-first database for teams and agents: every value carries sources, rules and coverage.
