Marmot for Agents
An agent acting without context is guessing. It doesn't know which table holds customer orders, who owns the payments service, what a column means, or what breaks downstream if it changes something. Marmot for Agents ends that context starvation: it plugs your LLM agents into the catalog so they read it for context and write back the lineage they generate.
What your agents can do
Discover assets
Find any service, API, queue, topic, table or pipeline by name, type or metadata.
Resolve ownership
Answer who owns an asset and who to contact before acting on it.
Understand meaning
Pull business definitions and glossary terms so answers use your language.
Trace lineage
See upstream and downstream dependencies to reason about impact.
Two ways to connect
MCP Server
The fastest path: point any client that speaks MCP (Claude, Cursor, ChatGPT, Cline) at Marmot and start asking.
SDK
Build agents directly against the catalog with the typed Python, Go or TypeScript client.