Introduction

Marmot gives people and AI agents one governed way in to your data. It catalogs the tables, topics, dashboards and pipelines you already run, records what each one means and who owns it, and serves that context in the web UI, over the API and to agents through its MCP server.

People and agents can also run SQL through Marmot against the sources you connect. Each query is checked against the caller's roles before it reaches the database, and the query audit records who ran what and what came back, so an agent never needs a database password of its own.

Start here

• Quick startRun Marmot locally with Docker Compose and catalog your first assets in about five minutes.
• Marmot CloudLaunch a managed instance in about a minute. The free plan needs no card.

What you can do with it

• Find the right assetSearch every source in plain words, then narrow the results with the query language.
• Explain what it meansOwners, descriptions, glossary terms and data products travel with every asset.
• See where data flowsLineage from your plugins and OpenLineage runs, upstream and downstream.
• Decide who can read whatRoles for people, teams and agents. Marmot Cloud adds grants per table, data product and term.
• Give agents contextConnect Claude, Cursor and any MCP client to the catalog, or build on the SDKs.
• Keep it current70+ plugins read your sources on a schedule, and asset rules enrich what arrives.

How it fits together

Plugins read metadata from the systems you already run into one catalog: schemas, owners, descriptions and lineage. People use it in the web UI, agents through the MCP server and your own code through the API, CLI and SDKs, so everyone works from the same answers.

• +60

Marmot

• Catalog
• Glossary
• Lineage
• Access

• People
• Agents
• Your code

Plugins read metadata from PostgreSQL, Snowflake, BigQuery, Kafka, dbt, Airflow, S3, Looker and more than 60 other systems into Marmot's catalog, glossary, lineage and access rules. People read it in the web UI, agents through the MCP server, and your code through the API, CLI and SDKs.

Where to run it

Marmot is one Go binary backed by PostgreSQL, and the core is open source under the MIT licence. Everything in these docs applies wherever it runs: the data model, the query language, the plugins and the MCP server are the same in every edition.

• Marmot CloudWe run it for you, with access control per resource, secret stores and keyless pipelines.
• Run it yourselfDocker Compose, Helm or the single binary, on any cloud or your own hardware.

Get help

• Discord (opens in a new tab)Ask questions and talk to the team and other people running Marmot.
• GitHub (opens in a new tab)Open an issue, read the code or send a pull request.
• BlogGuides and engineering writing from the Marmot team.
• Report a vulnerabilityHow to tell us about a security issue, privately.